About the role

We are seeking a Staff Software Engineer to build and operate the safety, oversight, and intervention mechanisms that protect Claude on third-party cloud service provider (CSP) platforms. As the engineer responsible for Safeguards on those surfaces, you will ensure that every request served through our CSP partners is monitored for misuse, enforced against policy, and compliant with the data residency and privacy commitments that enterprise CSP customers expect.

You will sit at the seam between the Safeguards organization and the Cloud Inference team: taking classifiers, detection signals, and enforcement policies developed by Safeguards and making them run reliably inside a CSP partner’s infrastructure at serving-path latency and scale. You will own the architecture that lets our safeguards operate within those constraints without gaps. You will build, deploy and operate the multi-layered defenses that catch unwanted model behavior in real time, the telemetry pipelines that give us situational awareness over CSP traffic, and the enforcement hooks that let us act quickly when something goes wrong. Your work will directly determine whether Anthropic can ship frontier models on CSP platforms at the same safety bar we hold ourselves to on our first-party API.

Responsibilities:

• Build, deploy and operate real-time safeguards infrastructure—classifiers, rate limits, enforcement actions, and intervention hooks—embedded directly in the third-party CSP inference serving path
• Design and maintain the data residency and privacy architecture for safeguards signals on CSP platforms, ensuring we can detect abuse and monitor model behavior while honoring regionalization boundaries and enterprise contractual commitments
• Develop telemetry, logging, and evaluation pipelines that give Safeguards, Policy, and T&S operational teams situational awareness over CSP traffic and close the visibility gap between third-party and first-party serving
• Dive into the CSP serving stack to identify the lowest-impact points to gather signals or introduce interventions without degrading latency, stability, or overall architecture
• Hold a high operational bar: own on-call, drive root-cause analyses and postmortems for safeguards incidents on CSP platforms, and build systems that reduce the human intervention required to keep Claude safe
• Work closely with Safeguards research, Policy & Enforcement, the Cloud Inference team, and CSP partner contacts to turn detection research and policy decisions into production enforcement that works inside a partner’s cloud.

You may be a good fit if you:

• Have a Bachelor’s degree in Computer Science, Software Engineering, or comparable experience
• Have 7+ years of experience in high-scale, high-reliability software development, ideally with exposure to trust & safety, anti-abuse, fraud, or integrity systems
• Are proficient in Python and comfortable working across the stack—from request-path services to data pipelines to internal tooling
• Think adversarially: you can see a system from a bad actor’s perspective, anticipate how they will respond to countermeasures, and design defenses in depth rather than single points of enforcement
• Have experience scaling infrastructure to accommodate rapid traffic growth while keeping latency and reliability within tight budgets
• Are deeply interested in the potential transformative effects of advanced AI systems and are committed to ensuring their safe development
• Have strong communication skills and can explain complex technical and risk tradeoffs to non-technical stakeholders across Policy, Legal, and partner organizations
• Enjoy working in a fast-paced, early environment; comfortable with adapting priorities as driven by the rapidly evolving AI space

Strong candidates may also have experience with:

• Building trust and safety, anti-spam, fraud, or abuse detection and mitigation mechanisms for AI/ML systems, or the infrastructure to support these systems at scale
• Machine learning serving infrastructure (GPUs/TPUs, inference servers, load balancing) and the operational realities of running models in production
• Major cloud platform internals—IAM, Network/service perimeter controls, regional resource constraints, cloud-native logging/monitoring—or experience shipping software that runs inside a partner’s cloud rather than your own
• Data residency, privacy engineering, or compliance-constrained architectures, particularly where telemetry has to stay within regional or contractual boundaries
• Working closely with operational and human-review teams to build custom internal tooling, admin UX, and alerting
• Adversarial mindset: has shipped defenses against motivated attackers before, knows what it feels like when they adapt, and can sprint to close a gap before it becomes an incident
• Comfortable operating at the intersection of platform/infra engineering and trust & safety—neither a pure infra engineer nor a pure T&S engineer, but someone who can credibly do both
• Has shipped software that runs inside someone else’s infrastructure (partner cloud, embedded deployment, or similar) and knows how to get things done when you don’t control the whole stack
• Senior enough to own a cross-team seam independently, drive consensus across orgs, and make latency/safety tradeoff calls without escalation
• TypeScript or Rust, and agentic coding tools such as Claude Code

About the Role

Anthropic is an AI safety and research company working to build reliable, interpretable, and steerable AI systems. We want AI to be safe and beneficial for our customers and society as a whole. As a Safeguards Analyst focusing on Account Abuse, you will play a critical role in building and scaling the detection, enforcement, and operational capabilities that protect our platform against scaled abuse.

Important Context: In this position, you may be exposed to and engage with explicit content spanning a range of topics, including those of a sexual, violent, or psychologically disturbing nature. There is also an on-call responsibility across the Policy and Enforcement teams.

Responsibilities:

• Develop and iterate on account signals and prevention frameworks that consolidate internal and external data into actionable abuse indicators
• Develop and optimize identity and account-linking signals using graph-based data infrastructure to detect coordinated and scaled account abuse
• Evaluate, integrate, and operationalize third-party vendor signals — assessing whether new data sources provide genuine lift in detection
• Expand internal account signals with new data sources and behavioral indicators to improve detection coverage
• Build and maintain processes that evaluate new product launches for scaled abuse risks, working closely with product teams to ensure enforcement readiness
• Operationalize and iterate on enforcement tooling — including appeals workflows, review processes, and user communications — to maintain quality and scale with growing volume
• Analyze enforcement performance through operational metrics, partnering with the team to keep detection accurate as abuse patterns evolve
• Manage payment fraud and dispute operations to protect revenue and maintain our standing with payment partners
• Coordinate enforcement efforts for policy compliance gaps across products, working with relevant teams to build scalable review processes
• Collaborate with cross-functional teams (Engineering, Product, Legal, Data Science) to surface new signals and translate detection capabilities into enforcement workflows
• Maintain detailed documentation of signal development, enforcement processes, and operational decisions

Qualifications:

• 2+ years of experience in risk scoring, fraud detection, trust and safety, or policy enforcement
• Hands-on experience building detection systems, risk models, or enforcement processes and workflows
• Experience evaluating and integrating third-party data sources into detection or scoring pipelines
• Strong SQL and Python skills — this role involves heavy data analysis across complex, multi-table data relationships
• Familiarity with identity signals such as device fingerprinting, account linking, or entity resolution, or experience with appeals processes and customer-facing enforcement communications
• Demonstrated ability to analyze complex data problems and translate findings into actionable improvements
• Strong written and verbal communication skills — ability to explain technical tradeoffs and navigate cross-functional stakeholder conversations
• Equivalent practical experience or a Bachelor's degree in Computer Science, Data Science, or related field

You might be a good fit if you:

• Have built risk scores, detection systems, signal pipelines, or enforcement processes in a previous role — identity verification, trust and safety, or similar
• Are comfortable working with ambiguous, noisy data and extracting meaningful signal
• Think critically about signal quality and enforcement performance — evaluating whether new detection signals or processes meaningfully improve outcomes
• Have experience with graph-based data, account-linking problems, or cross-functional process design
• Are proactive about identifying gaps in existing detection or enforcement and proposing new approaches
• Have experience leveraging generative AI tools to support analytical, detection, or enforcement workflows
• Can balance deep analytical work with cross-functional collaboration and stakeholder coordination
• Have a background or interest in cybersecurity or threat intelligence (a plus, not a requirement)

About this Role

This role offers a unique opportunity to shape how AI systems handle sensitive chemical and explosives information. You'll work with leading AI safety researchers while tackling critical problems in preventing catastrophic misuse. If you're excited about using your expertise to ensure AI systems remain safe and beneficial, we want to hear from you.

Responsibilities:

• Design and implement evaluation methodologies for assessing AI model capabilities relevant to chemical weapons, explosives synthesis, and energetic materials
• Develop and execute strategies to identify and mitigate potential C/E misuse in model outputs
• Create C/E threat models, including precursor identification, synthesis routes, and weaponization techniques
• Review and analyze traffic to identify potential policy violations related to C/E content
• Collaborate with software engineers to develop and refine detection systems and automated enforcement tools for C/E threats
• Conduct rapid response to escalations involving dangerous C/E queries
• Collaborate across teams to establish safety benchmarks and develop appropriate model guardrails
• Translate C/E domain knowledge into actionable safety requirements
• Develop approaches to assess C/E model knowledge boundaries for dual-use chemical information
• Monitor emerging threats in the C/E landscape to inform policy development

You may be a good fit if you:

• Have a Ph.D. in Chemistry, Chemical Engineering, or a related field with focus on energetic materials, explosives, and/or chemical weapons
• Have 5-8+ years of experience in chemical weapons and/or explosives defense, with deep expertise in energetic materials, chemical weapon agents, or related areas
• Have knowledge of high yield explosives application to radiological dispersal devices (dirty bombs) and related radiological weapons
• Have a track record of translating specialized technical knowledge into actionable safety policies or guidelines
• Are comfortable navigating ambiguity and developing solutions for novel safety challenges
• Can work independently while maintaining strong collaboration with cross-functional teams including engineering, enforcement, and research
• Thrive in a fast-paced environment where you balance rigorous scientific standards with rapid threat response
• Are passionate about preventing misuse of dangerous technical knowledge while enabling beneficial applications

Strong candidates may have:

• Experience with both chemical weapons and high yield explosives defense
• Experience working with defense, intelligence, or nonproliferation organizations (e.g., OPCW, IAEA, national labs, defense contractors)
• Published research or practical experience in explosives characterization, chemical weapons detection, or related security applications
• Knowledge of international chemical weapons conventions (CWC) and controlled substances regulations
• Demonstrated ability to communicate complex technical concepts to non-specialist audiences
• Experience with chemical databases (PubChem, Reaxys, SciFinder) and computational chemistry tools
• Understanding of radiological materials and their interaction with explosive dispersal mechanisms
• Familiarity with dual-use C/E research concerns and responsible disclosure practices

About the Role

We are looking for biological scientists to help build safety and oversight mechanisms for our AI systems. As a Safeguards Biological Safety Research Scientist, you will apply your technical skills to design and develop our safety systems which detect harmful behaviors and to prevent misuse by sophisticated threat actors. You will be at the forefront of defining what responsible AI safety looks like in the biological domain, working across research, policy, and engineering to translate complex biosecurity concepts into concrete technical safeguards. This is a unique opportunity to shape how frontier AI models handle dual-use biological knowledge—balancing the tremendous potential of AI to accelerate legitimate life sciences research while preventing misuse by sophisticated threat actors.

In this role, you will:

• Design and execute capability evaluations ("evals") to assess the capabilities of new models
• Collaborate closely with internal and external threat modeling experts to develop training data for our safety systems, and with ML engineers to train these safety systems, optimizing for both robustness against adversarial attacks and low false-positive rates for legitimate researchers
• Analyze safety system performance in traffic, identifying gaps and proposing improvements
• Develop rigorous stress-testing of our safeguards against evolving threats and product surfaces
• Partner with Research, Product, and Policy teams to ensure biological safety is embedded throughout the model development lifecycle
• Contribute to external communications, including model cards, blog posts, and policy documents related to biological safety
• Monitor emerging technologies for their potential to contribute to new risks and new mitigation strategies, and strategically address these

You may be a good fit if you have

• A PhD in molecular biology, virology, microbiology, biochemistry, systems or computational biology, or a related life sciences field, OR equivalent professional experience 
• Extensive experience in scientific computing and data analysis, with proficiency in programming (Python preferred)
• Deep expertise in modern biology, including both "reading" (e.g. high-throughput measurement, functional assays) and "writing" (gene synthesis, genome editing, strain construction, protein engineering) techniques in biology
• Familiarity with dual-use research concerns, select agent regulations, and biosecurity frameworks (e.g., Biological Weapons Convention, Australia Group guidelines)
• Strong analytical and writing skills, with the ability to navigate ambiguity and explain complex technical concepts to non-technical stakeholders
• Have a passion for learning new skills and an ability to rapidly adapt to changing techniques and technologies
• Comfort working in a fast-paced environment where priorities may shift as AI capabilities evolve

Preferred Qualifications

• Background in AI/ML systems, particularly experience with large language models
• Experience in developing ML for biological systems
• Extensive experience in complex projects with multiple stakeholders

About the role

The Safeguards team is responsible for the systems that detect, review, and act on misuse of Anthropic's models — work that sits at the very centre of our mission to develop AI safely. Within Safeguards, the Foundations team builds the platforms, infrastructure, and internal tools that the rest of the organisation depends on to do this well.

We are looking for a software engineer to own and extend the internal tooling that powers human review — the case management, labelling, investigation, and enforcement interfaces our analysts and policy specialists use every day. These are back-office tools, but they are anything but low-stakes: the speed, clarity, and reliability of this tooling directly determines how quickly Anthropic can identify harmful behaviour, make sound enforcement decisions, and feed signal back into model training. You'll work closely with Trust & Safety operations, policy, and detection-engineering teams to turn messy operational workflows into well-designed, durable software.

This is a hands-on, full-stack role for someone who enjoys building products for internal users, sweats the details of usability and correctness, and wants their engineering work to have a clear line to real-world safety outcomes.

Responsibilities

• Design, build, and maintain the internal review and enforcement tooling used by Safeguards analysts — including case queues, content review surfaces, decision/audit logging, and account-actioning workflows
• Understand user workflows and establish tooling for well processes that may be distributed across a number of tools and UIs
• Develop the ‘base layer’ of reusable APIs, data storage, and backend services that let new review workflows be stood up quickly and safely
• Partner with operations and policy teams to understand reviewer pain points, then translate them into clear product improvements that reduce handling time and decision error
• Integrate tooling with upstream detection systems and downstream enforcement infrastructure so that flagged behaviour flows cleanly from signal → human review → action
• Build in the guardrails that sensitive internal tools require: granular permissions, audit trails, data-access controls, and reviewer wellbeing features (e.g. content blurring, exposure limits)
• Instrument the tools you ship — surfacing metrics on queue health, reviewer throughput, and decision quality so the team can see what's working
• Contribute to the Foundations team's shared platform and on-call responsibilities

You may be a good fit if you

• Have 4+ years of experience as a software engineer, with meaningful time spent building internal tools, operations platforms, or back-office products
• Are comfortable using agentic coding tools (e.g. Claude Code) as a core part of your workflow, and can direct them to ship well-tested, production-quality software at a high cadence without lowering the bar (our stack is mostly React/TypeScript and Python)
• Take a product-minded approach to internal users: you work with the people using your tools, watch where they struggle, and fix it
• Are results-oriented, with a bias towards flexibility and impact
• Pick up slack, even if it goes outside your job description
• Communicate clearly with non-engineering stakeholders and can explain technical trade-offs to operations and policy partners
• Care about the societal impacts of your work and want to apply your engineering skills directly to AI safety

Strong candidates may also

• Have built tooling in a trust & safety, content moderation, fraud, integrity, or risk-operations setting
• Have experience designing case-management or workflow systems (queues, SLAs, escalation paths, audit logs)
• Have worked with sensitive data and understand the privacy, access-control, and reviewer-wellbeing considerations that come with it
• Have experience with GCP/AWS, Postgres/BigQuery, and CI/CD in a production environment
• Have used LLMs as a building block inside operational tools (e.g. assisted triage, summarisation, or classification in the review loop)

Representative projects

• Rebuilding the analyst review queue so cases are routed by severity and skill, with full decision history and one-click escalation
• Shipping a unified account-investigation view that pulls signals from multiple detection systems into a single, permissioned surface
• Adding content-obfuscation and exposure-tracking features to protect reviewers working with harmful material
• Building an internal labelling tool that feeds high-quality ground truth back to the detection and research teams

Candidates need not have

• 100% of the skills listed above
• Prior experience in AI or machine learning
• Formal certifications or education credentials

Deadline to apply: None. Applications will be reviewed on a rolling basis.

About the Role

As a Safeguards Policy Analyst focused on Fraud & Scams, you will be responsible for designing, building, and executing enforcement workflows that detect and mitigate fraud and scam-related harms on Anthropic's products. You will serve as the subject matter expert on fraud typologies, scam ecosystems, and the threat actors who perpetrate them — translating that expertise into durable and scalable policies. 

This role sits within the Integrity & Authenticity (I&A) team, You will function both as a policy owner, and work closely with threat investigative and enforcement teams.  You will also develop the guidelines that power classifiers, and will be our point of content  cross-functional workstreams. No two days will look the same.

Important context: In this position you may be exposed to and engage with explicit content spanning a range of topics, including those of a financial, psychological, or otherwise disturbing nature, including detailed fraud schemes and scam content.

Responsibilities: 

Policy Design & Ownership

• Draft, maintain, and iterate on Fraud & Scams policies governing Anthropic's products and APIs, with clarity for both model enforcement and human reviewers
• Conduct regular structured policy reviews to identify gaps, ambiguities, and coverage failures, and lead the process to close them
• Develop detailed threat models for fraud and scam vectors — including social engineering, financial fraud, impersonation scams, phishing, and AI-enabled fraud — and translate these into enforceable policy language
• Stay current on the fraud and scam landscape, including emerging typologies, regulatory shifts, and threat actor tactics, techniques, and procedures (TTPs)

Enforcement Strategy & Operations

• Design and architect automated enforcement systems and human review workflows that scale effectively while maintaining high precision and recall
• Review flagged content to drive enforcement decisions and surface policy improvements grounded in real-world cases
• Define and manage precision/recall tradeoffs in enforcement, working with data science teams to continuously tune classifiers and detection signals
• Build and maintain an effective feedback loop between threat intelligence, policy, and enforcement operations to ensure timely response to novel and evolving fraud threats

Technical & Cross-functional Collaboration

• Serve as the primary policy point of contact for ML and Engineering teams developing fraud detection classifiers, working to translate policy intent into technical artifacts and training signals
• Partner with Product, Engineering, and Data Science teams to optimize detection models, automated enforcement pipelines, and tooling for fraud-specific policy violations
• Collaborate with external researchers, law enforcement liaisons, and fraud SMEs to gather feedback on policy effectiveness and emerging risk areas

Stakeholder Alignment & Education

• Educate and align internal stakeholders — including Legal, Public Policy, and Go-to-Market teams — around Anthropic's fraud and scams policies and enforcement approach
• Serve as an internal resource on fraud risk, briefing leadership and cross-functional partners as threats evolve
• Contribute to Anthropic's external communications and policy documentation related to fraud and platform integrity where relevant

You may be a good fit if you have experience:

• Working as a Trust & Safety professional with a focused background in fraud, scams, or financial crime — particularly in a tech platform or AI context
• Writing, iterating on, and managing operational policies for fraud or abuse prevention at scale
• Threat modeling for fraud and scam ecosystems, including social engineering, romance scams, investment fraud, impersonation, and phishing
• Identifying and articulating common fraud tactics (e.g., pig butchering, advance fee fraud, account takeover facilitation) and how they manifest on AI platforms
• Using SQL or other data analysis tools to identify trends, measure enforcement efficacy, and surface policy gaps
• Collaborating cross-functionally with Engineering, ML, Legal, and Policy teams on safety initiatives
• Working with generative AI products, including writing effective prompts for content review and enforcement use cases
• Thriving in a fast-paced, ambiguous environment where priorities shift and the threat landscape evolves rapidly

Preferred Qualifications: 

• Experience at a major technology platform, financial institution, or fraud intelligence firm in a policy, operations, or investigative capacity
• Familiarity with the generative AI risk landscape and how large language models can be exploited for fraud and social engineering
• Background in threat intelligence, financial crimes compliance (AML/KYC), or law enforcement focused on cyber-enabled fraud
• Demonstrated ability to develop and communicate policy positions to diverse stakeholders including legal counsel and executive leadership

About the role

As a Safeguards Analyst focusing on human exploitation and abuse, you will be responsible for building and executing enforcement workflows that detect and mitigate the use of our products to facilitate human trafficking, sextortion, image-based sexual abuse, bullying, and harassment. As a member of the user well-being team, your initial focus will be on standing up detection, review, and escalation workflows for this domain — from tuning classifiers and curating evaluation datasets through to managing external partnerships and real-world harm escalation pathways. This position may later expand to include broader areas of user well-being enforcement. Safety is core to our mission, and you'll help shape policy enforcement so that our users can interact with and build on top of our products across all surfaces in a harmless, helpful, and honest way.

Important context

In this position, you may be exposed to and engage with explicit content spanning a range of topics, including those of a sexual, violent, or psychologically disturbing nature. There is also an on-call responsibility across the Policy and Enforcement teams.

Responsibilities:

• Design and architect automated enforcement systems and review workflows for human exploitation and abuse, ensuring they scale effectively while maintaining high accuracy

• Partner with Product, Engineering, and Data Science teams to build and tune detection signals for human trafficking, sextortion, and image-based sexual abuse, and to develop custom mitigations for these sensitive policy areas

• Curate policy violation examples, maintain golden evaluation datasets, and track enforcement actions across both consumer and API surfaces

• Conduct deep-dive investigations into suspected exploitation activity — using SQL and other data analysis tools to surface threat patterns and bad-actor behavior in large datasets — then produce clear, well-sourced intelligence reports that inform detection strategy and surface policy gaps to the Safeguards policy design team

• Study trends internally and in the broader ecosystem — including evolving trafficking and sextortion tactics — to anticipate how AI systems could be misused for exploitation as capabilities advance

• Review and investigate flagged content to drive enforcement decisions and policy improvements, exercising careful judgment on the line between permitted adult content and exploitative material

• Build and maintain relationships with external intelligence partners — including hotlines, NGOs, and industry hash-sharing consortia — to inform our approach and enable appropriate real-world escalation

You may be a good fit if you have:

Required

• 3+ years of experience in trust and safety, content moderation, counter-exploitation work, or a related field

• Subject matter expertise in one or more of: human trafficking, human exploitation and abuse, sextortion, image-based sexual abuse / non-consensual intimate imagery, or commercial sexual exploitation

• Experience building or operating detection and review workflows for sensitive content, at a platform, NGO, hotline, or similar organization

• Ability to use SQL, Python, and/or other data analysis tools to interact with large datasets and derive insights that support key decisions and recommendations

• Demonstrated ability to analyze complex situations and make well-reasoned decisions under pressure

• Sound judgment in distinguishing permitted content from exploitative content, and comfort working in areas where these lines require careful reasoning

• Strong attention to detail and ability to maintain accurate documentation

• Ability to collaborate with team members while navigating rapidly evolving priorities and workstreams

Preferred

• Familiarity with the NGO and industry ecosystem working on these harms (for example, Polaris Project, Thorn, NCMEC, IWF, StopNCII, or industry hash-sharing initiatives)

• Experience conducting open-source investigations or threat actor profiling in a trust & safety, intelligence, or law enforcement context

• Experience working with generative AI products, including writing effective prompts for content review and enforcement

• A deep interest in AI safety and responsible technology development

• Experience standing up real-world harm escalation pathways or working with law enforcement referral processes

About the role

As the Vendor and Contract Manager on the Safeguards team, you will own the end-to-end lifecycle of Anthropic's safety-critical vendor, partner, and consultant relationships — from identifying and selecting vendors through contract negotiation, onboarding, ongoing performance management, and renewal. The vendors and partners you'll manage span verification, threat intelligence, process outsourcing, capability evaluation, civil society consultation, and research collaboration.

You'll build repeatable processes where they're needed while staying nimble enough to handle novel partnership structures, like research collaborations, civil society consultations, and model red-teaming engagements that don't fit neatly into standard procurement workflows. You'll work closely with legal, procurement, finance, and engineering teams, and you'll be the person who knows where every Safeguards contract stands, what we're spending, and where we should consider a change.

This is a role for someone who's comfortable operating across commercial, legal, and technical contexts in a fast-moving environment — someone who can negotiate contract terms, work with legal teams to redline contracts,  set up model access for a research partner, and handle a vendor performance issue in one day.

*Important context for this role: In this position you may be exposed to and engage with explicit content spanning a range of topics, including those of a sexual, violent, or psychologically disturbing nature.

Responsibilities:

Vendor Selection & Onboarding

• Understand the broad vendor landscape for Safeguards and drive vendor selection processes with expert input, factoring in tradeoffs between capability, price, and internal resources across categories including verification, threat intelligence, process outsourcing, and capability evaluation
• Conduct vendor due diligence and coordinate security and data governance reviews for vendors handling sensitive model access or content
• Forecast future partnership needs and proactively research vendors and partners that could meet emerging Safeguards requirements

Contract & Budget Management

• Manage contracts across the Safeguards vendor and partner portfolio, working with legal and procurement teams on contract redlining, negotiation, and execution
• Work with legal teams and potential research partners to develop novel agreements for research collaboration, civil society consultation, and model red-teaming
• Handle invoicing, payment, and renewal processes with partners
• Own Safeguards vendor budget tracking and planning in partnership with finance teams, maintaining a clear picture of current spend and forecasting future needs

Ongoing Vendor & Partner Management

• Manage vendor and researcher access to models and products during testing phases and trials
• Oversee and monitor vendor performance and usage, flagging issues and resolving concerns and disputes as they arise
• Report on vendor performance, spend, and contract status to Safeguards leadership

You may be a good fit if you have:

• 5+ years in vendor management, procurement, or contract operations, ideally in risk, fraud, compliance, or trust & safety contexts at a technology company
• Demonstrated experience reviewing and negotiating contracts, including comfort with redlining and working alongside legal counsel
• Track record managing vendor budgets, including forecasting, tracking spend, and making tradeoff recommendations
• Understanding of AI safety, account abuse, or platform integrity issues — you know what verification vendors, threat intelligence providers, and content screening tools actually do
• Experience onboarding vendors and standing up new vendor relationships from scratch, not just managing existing ones
• Strong cross-functional collaboration skills, particularly with legal, procurement, finance, and engineering teams
• Comfort with ambiguity and fast-moving environments — you've built or significantly improved vendor management processes, not just inherited them

Nice to have:

• Experience in AI safety or AI-adjacent vendor ecosystems
• Familiarity with procurement tools such as Ironclad or Zip

About the role           

Anthropic is looking for a Data Engineer to join the Safeguards team and build the data foundations that keep our AI systems safe. The Safeguards team works to monitor models, prevent misuse, and ensure user well-being — and doing that well requires robust, reliable data infrastructure. In this role, you'll design and build the data pipelines, warehousing solutions, and analytical tooling that power our safety and trust efforts at scale.

You'll work closely with engineers, data scientists, and policy teams to ensure the Safeguards organization has the data it needs to detect abuse patterns, measure the effectiveness of safety interventions, and make informed decisions about model behavior and enforcement. This is a high-impact role where your work will directly support Anthropic's mission to develop AI that is safe and beneficial.

Responsibilities:

- Design, build, and maintain scalable data pipelines that support safety monitoring, abuse detection, and enforcement workflows
- Develop and optimize data models and warehousing solutions to enable efficient analysis of large-scale usage and safety data
- Build and maintain dashboards and reporting infrastructure that give Safeguards teams visibility into model behavior, misuse patterns, and enforcement outcomes
- Collaborate with engineers to integrate data from multiple sources — including model outputs, user reports, and automated classifiers — into a unified analytical layer
- Implement data quality frameworks, monitoring, and alerting to ensure the reliability of safety-critical data
- Partner with research teams to surface data insights that inform model improvements and safety interventions
- Develop self-service data tooling that enables stakeholders to explore safety data and generate reports independently
- Contribute to data governance practices, including access controls, retention policies, and privacy-compliant data handling

You may be a good fit if you:

- Have 3+ years of experience in data engineering, analytics engineering, or a related role
- Are proficient in SQL and Python, with experience building and maintaining ETL/ELT pipelines
- Have hands-on experience with modern data stack tools such as dbt, Airflow, Spark, or similar orchestration and transformation frameworks
- Have worked with cloud data platforms (BigQuery, Redshift, Snowflake, or similar)
- Are comfortable building dashboards and data visualizations using tools like Looker, Tableau, or Metabase
- Communicate clearly and can translate complex data concepts for both technical and non-technical audiences
- Are results-oriented, flexible, and willing to pick up slack even when it falls outside your job description
- Care about the societal impacts of AI and are motivated by safety work

Strong candidates may have:

- Experience with trust & safety, integrity, fraud, or abuse detection data systems
- Experience with large-scale event streaming systems (Kafka, Pub/Sub, Kinesis)
- Built data infrastructure that supports ML model monitoring or evaluation
- Familiarity with data privacy and compliance frameworks (GDPR, CCPA, or similar)
- A background in statistical analysis, or experience collaborating closely with data scientists
- Developed internal tooling or self-service analytics platforms

Strong candidates need not have:

- A formal degree in Computer Science or a related field — we value practical experience and demonstrated ability over credentials
- Prior experience in AI or machine learning — you'll learn the domain-specific context on the job
- Previous experience at an AI safety or research organization
- Deep expertise across every tool listed above — familiarity with a subset and a willingness to learn is enough

About the role

As a Safeguards Policy Design Manager, you will be responsible for developing usage policies, clarifying enforcement guidelines, and advising on safety interventions for our products and services. Your core focus will be on age-appropriate design and experiences, including child safety, age assurance, content classification, and adult sexual content. You will help define best practices for developers building on claude for deployment to users across different developmental stages, design age-assurance policies that protect minors from inappropriate content and interactions, and establish clear boundaries for adult content and experiences. In addition, you will advise teams on opportunities for age-appropriate helpfulness, including advising cross-functional teams on beneficial use cases for younger users where appropriate. Safety is core to our mission and you’ll help shape policy creation and development so that our users can safely interact with and build on top of our products in a harmless, helpful and honest way.

*Important context for this role: In this position you may be exposed to and engage with explicit content spanning a range of topics, including those of a sexual, violent, or psychologically disturbing nature.

Responsibilities:

• Serve as an internal subject matter expert, leveraging deep expertise in child safety, adult content, youth development, and age-appropriate design to:

  • Draft new policies that help govern the responsible use of our models for emerging capabilities and use cases

  • Design evaluation frameworks for testing model performance in areas of expertise

• Conduct regular reviews and testing of existing policies to identify and address gaps and ambiguities

• Review flagged content to drive enforcement and policy improvements

• Update our usage policies based on feedback collected from external experts, our enforcement team, and edge cases that you will review

• Work with safeguards product teams to identify and mitigate concerns, and collaborate on designing appropriate interventions for users across different age groups

• Advise on age assurance approaches and content classification frameworks in partnership with Enforcement, Product, Engineering, and Legal teams

• Educate and align internal stakeholders around our policies and our approach to safety in your focus area(s)

• Keep up to date with new and existing AI policy norms, regulatory requirements (e.g., age-appropriate design codes), and industry standards, and use these to inform our decision-making on policy areas

You may be a good fit if you have experience:

• As a researcher, subject matter expert, or trust & safety professional working in one or more of the following focus areas: child safety, youth online safety, age assurance, developmental science, content classification and rating systems, or adult content policy. Note: For this role, an advanced degree in developmental psychology, child development, education, or a related field is preferred.

• Drafting or updating product and / or user policies, with the ability to effectively bridge technical and policy discussions

• Designing or implementing age-appropriate experiences, age assurance mechanisms, or content classification / labeling systems

• Working with generative AI products, including writing effective prompts for policy evaluations and classifier development

• Aligning product policy decisions between diverse sets of stakeholders, such as Product, Engineering, Public Policy, and Legal teams

• Understanding the challenges that exist in developing and implementing product policies at scale, including in the content moderation space

• Thinking creatively about the risks and benefits of new technologies, and leveraging data and research to inform policy recommendations

• Navigating and prioritizing work efforts amidst ambiguity

About the role

The Account Abuse team is tasked with ensuring Anthropic’s computing capacity is allocated fairly, minimizing resources available to bad actors and preventing them from coming back. As a software engineer on this team, you will build systems that gather and analyze signals at scale, balancing tradeoffs and coordinating closely with stakeholder teams throughout the company. The ideal candidate can see things from opponents’ perspectives, understand their means and motives, and anticipate their responses to countermeasures.

Responsibilities:

• Ability to think and respond quickly in a rapidly-changing greenfield environment
• Jumping into other teams’ code to identify key points to gather signals or introduce interventions with minimal impact on their systems’ stability, complexity, or overall architecture
• Integration with third-party data-enrichment vendors
• Creating monitoring dashboards, alerts, and internal admin UX
• Working closely with our data scientists to maintain situational awareness of our current usage patterns and trends, and with our Policy & Enforcement team to maximize the impact of their human-review availability
• Building robust and reliable multi-layered defenses
• Lead root cause analyses and deep-dive investigations into account activity to identify abuse patterns, uncover emerging attack vectors, and inform both immediate enforcement actions and longer-term systemic defenses

You may be a good fit if you have:

• A Bachelor’s degree in Computer Science, Software Engineering or comparable experience
• 5-10+ years of experience in a software engineering position, preferably with a focus on integrity, spam, fraud, or abuse detection.
• Proficiency in Python, SQL, and data analysis tools.
• Strong communication skills and ability to explain complex technical concepts to non-technical stakeholders

Strong candidates may also:

• Have experience building trust and safety mechanisms for and using AI/ML systems, such as fraud-detection models or security monitoring tools or the infrastructure to support these systems at scale
• Have worked closely with operational teams to build custom internal tooling

About the Role

We are looking for vulnerability researchers to help mitigate the risks that come with building AI systems. One of these risks is the potential for LLMs to enable adversaries to cause harm by automating the attacks that today are carried out by human cybercrime groups, but in the future may be easily carried out by humans misusing LLMs. We are hiring security specialists who are experienced at exploitation and remediation, and are interested in understanding how LLMs could cause harm in the future, so that we can better prepare for this future and mitigate these risks before they arise.

Responsibilities: 

• Triage any vulnerabilities discovered, coordinate and assist the external and open-source community in remediation
• Write scaffolds designed to automate typical traditional attack techniques to help clarify our defensive problem selection
• Research how adversaries might mise-use LLMs to identify and exploit vulnerabilities at scale in the future
• Develop promising defensive strategies that could mitigate the ability of adversaries to mis-use models in harmful ways
• Work with a small, senior team of engineers and researchers to enact a forward-looking security plan

You may be a good fit if you have: 

• 3+ years experience with pentesting, vulnerability research, or other offensive security experience
• Senior-level knowledge in at least one related topic area (reverse engineering, network security, exploitation, physical security)
• A history demonstrating desire to do the “dirty work” that results in high-quality outputs
• Software engineering experience
• Demonstrated success in bringing clarity and ownership to ambiguous technical problems
• Proven ability to lead cross-functional security initiatives and navigate complex organizational dynamics

Strong candidates may also have:

• Published research papers on computer security, language modeling, or related topics; or given talks at Defcon, Blackhat, CCC, or related venues
• Familiarity with large language models and how they work; for example, you may have written agent scaffolds
• Reported CVEs, or been awarded for bug bounty vulnerabilities
• Contributed to open-source projects in LLM- or security-adjacent repositories

About the role

Anthropic's Safeguards team is responsible for the systems that allow us to deploy powerful AI models responsibly — and the data infrastructure underneath those systems is foundational to getting that right. The Safeguards Data Infrastructure team owns the offline data stack that underpins our safeguards work: the storage layer for sensitive user data, the tooling built on top of it, and the interfaces that let the rest of the Safeguards organization access that data safely and ergonomically.

As Engineering Manager of this team, you'll be responsible for ensuring full portability of our safeguards data stack across an expanding set of deployment environments, building privacy-preserving data interfaces that enable ML and training workflows, and driving compliance with data regulations including HIPAA. This is a role at the intersection of infrastructure engineering, data privacy, and enterprise product requirements — and it sits at a critical juncture as Anthropic scales into new cloud environments and geographies

Responsibilities:

• Lead and grow a team of engineers delivering the data infrastructure and tooling that powers Anthropic's safeguards capabilities
• Own the strategy and execution for porting the safeguards offline data stack — including PII storage and tooling — across new cloud and deployment environments as Anthropic expands
• Build and maintain privacy-safe data APIs and interfaces that enable ML and training workflows while respecting data retention and access constraints
• Drive tooling and architecture decisions that maximize data retention within the bounds of our privacy and compliance requirements
• Manage privacy incident response processes and partner with compliance teams on regulatory requirements (e.g. HIPAA, EU privacy regulations)
• Collaborate closely with enterprise customers and product teams on zero data retention offerings, working balancing safety needs with robust enterprise data contracts
• Independently own and drive multiple workstreams, including planning, execution, and cross-team coordination
• Coach, mentor, and support the career development of your direct reports, helping them set and achieve their professional goals
• Partner with recruiting to attract, hire, and retain strong engineering talent

You may be a good fit if you:

• Have 4+ years of front-line engineering management experience
• Have a track record of leading teams that build and operate data infrastructure at scale
• Have hands-on software engineering experience as an individual contributor prior to moving into management
• Have a strong understanding of data privacy principles, PII handling, and compliance frameworks
• Are comfortable driving technical decisions in an ambiguous, fast-moving environment with competing priorities
• Have experience working cross-functionally across infrastructure, product, and compliance or security teams
• Are clear and persuasive communicators, both in writing and in person

Strong candidates may also:

• Have experience with multi-cloud or multi-region data portability, particularly in regulated environments
• Have built privacy-preserving data pipelines or interfaces for ML workloads
• Have experience with enterprise data contracts or zero data retention architectures
• Have explored novel approaches to data processing under strict access constraints, such as in-memory storage and compute for sensitive data
• Have a passion for building diverse and inclusive teams

About the Role

We are looking for a Threat Collections Engineer to join our Threat Intelligence team. In this role, you will build the infrastructure that powers our threat discovery capabilities—integrating external data sources, developing detection systems for automated lead generation, and creating internal tooling that scales our investigators' impact.

This is a foundational engineering role on a small, high-impact team. You will take projects from proof-of-concept to production, work closely with investigators to understand their needs, and help scale what may become a multi-person collections function.

Responsibilities:

• Build automated detection systems that use disparate signals to identify abusive behavior. 
• Take systems from idea to proof-of-concept to production-grade with appropriate monitoring, documentation, and maintenance processes
• Develop and maintain YARA rule infrastructure, including tools for writing, validating, and testing rules against real data
• Create integrations with external threat intelligence platforms (e.g. VirusTotal, Censys, Urlscan) via MCP servers to enable multi-source correlation during investigations
• Build data pipelines that ingest intelligence from RSS feeds, CTI news sources, and partner sharing, using Claude to extract TTPs and generate targeted hunting queries
• Develop behavioral analytics capabilities using DBT-based frameworks and create searchable audit logging infrastructure
• Establish feedback loops with investigators to tune detection systems and reduce false positives
• Scrape and normalize data from external sources to feed threat detection and enrichment workflows

You may be a good fit if you:

• Have strong coding proficiency in Python and SQL for building detection logic, data pipelines, and automation
• Have experience with data pipeline orchestration tools (Airflow, DBT, or similar)
• Have familiarity with threat intelligence concepts including IOCs, YARA rules, and threat correlation techniques
• Have experience integrating external APIs and building data ingestion systems
• Can translate investigator needs and workflows into technical requirements
• Are comfortable building v0 systems and iterating based on user feedback
• Have strong communication skills for working closely with non-engineering stakeholders

Strong candidates may also have:

• Experience with threat intelligence sharing frameworks (e.g. MISP, STIX/TAXII)
• Background in cyber threat intelligence, security operations, or abuse detection
• Experience building MCP servers or similar tool integrations for AI systems
• Familiarity with web scraping and data extraction at scale
• Experience with behavioral analytics or anomaly detection systems
• Understanding of LLM capabilities and how to leverage them for automation
• A Top Secret Clearance 

Deadline to apply:
None. Applications will be reviewed on a rolling basis.

About the role

We are looking for software engineers to help build the foundational pieces for safety, oversight and intervention mechanisms of our AI systems. As a software engineer on the Safeguards team, you will work to monitor models, prevent misuse, and ensure user well-being. This role will focus on building systems to detect unwanted model behaviors and prevent disallowed use of models. You will apply your technical skills to uphold our principles of safety, transparency, and oversight.

Responsibilities:

• Develop the foundational systems which power Safeguards, including infrastructure for data storage and management, metric and evaluation systems, and tooling for human and agentic review.
• Ensure the day-to-day running of Safeguards systems and hold a high operational bar which serves both safety and customers while reducing the amount of human intervention and oversight required.
• Build robust and reliable multi-layered defenses for real-time improvement of safety mechanisms that work at scale

You may be a good fit if you have:

• Bachelor’s degree in Computer Science, Software Engineering or comparable experience
• 4-10+ years of experience in a software engineering position
• Proficiency in Python
• Ability to work across the stack
• Strong communication skills and ability to explain complex technical concepts to non-technical stakeholders

Strong candidates may also:

• Have experience building trust and safety, anti-spam, fraud or abuse detection and mitigation mechanisms and interventions for AI/ML systems
• Have experience building metrics and measurement systems or data and privacy management systems
• Have worked closely with operational teams to build custom internal tooling
• Be proficient in TypeScript or Rust
• Have experience with Claude Code or similar agentic coding tools

Deadline to apply: None. Applications will be reviewed on a rolling basis.

About the Role

We are looking for a Technical CBRN-E Threat Investigator to join our Threat Intelligence team. In this role, you will be responsible for detecting, investigating, and disrupting the misuse of Anthropic's AI systems for Chemical, Biological, Radiological, Nuclear, and Explosives (CBRN-E) threats. We are particularly interested in candidates with deep expertise in either chemical defense or biodefense.

You will work at the intersection of AI safety and CBRN security, conducting thorough investigations into potential misuse cases, developing novel detection techniques, and building robust defenses against threat actors who may attempt to leverage our AI technology for developing weapons, synthesizing dangerous compounds, or creating biological harm. Your specialized domain expertise will be critical to protecting against some of the most serious potential misuses of AI systems.

Important context: In this position you may be exposed to explicit content spanning a range of topics, including those of a sexual, violent, or psychologically disturbing nature. This role may require responding to escalations during weekends and holidays.

Responsibilities

• Detect and investigate attempts to misuse Anthropic's AI systems for developing, enhancing, or disseminating CBRN-E weapons, pathogens, toxins, or other threats to harm people, critical infrastructure, or the environment
• Conduct technical investigations using SQL, Python, and other tools to analyze large datasets, trace user behavior patterns, and uncover sophisticated CBRN-E threat actors
• Develop CBRN-E-specific detection capabilities, including abuse signals, tracking strategies, and detection methodologies tailored to dual-use research concerns
• Create actionable intelligence reports on CBRN-E attack vectors, vulnerabilities, and threat actor TTPs leveraging AI systems
• Conduct cross-platform threat analysis grounded in real threat actor behavior, open-source research, and publicly reported programs
• Collaborate with policy and enforcement teams to make informed decisions about user violations and ensure appropriate mitigation actions
• Engage with external stakeholders including government agencies, regulatory bodies, scientific organizations, and biosecurity/chemical security research communities
• Inform safety-by-design strategies by forecasting how threat actors may leverage advances in AI technology for CBRN-E purposes

You may be a good fit if you

• Have deep domain expertise in biosecurity, chemical defense, biological weapons non-proliferation, dual-use research of concern (DURC), synthetic biology, or related CBRN-E threat domains
• Have demonstrated proficiency in SQL and Python for data analysis and threat detection
• Have experience with threat actor profiling and utilizing threat intelligence frameworks
• Have hands-on experience with large language models and understanding of how AI technology could be misused for CBRN-E threats
• Have excellent stakeholder management skills and ability to work with diverse teams including researchers, policy experts, legal teams, and external partners
• Can present analytical work to both technical and non-technical audiences, including government stakeholders and senior leadership

Strong candidates may also have

• Advanced degree (MS or PhD) in biological sciences, chemistry, biodefense, biosecurity, or related field
• Real-world experience countering weapons of mass destruction or other high-risk asymmetric threats
• Experience working with government agencies or in regulated environments dealing with sensitive CBRN-E information
• Background in AI safety, machine learning security, or technology abuse investigation
• Familiarity with synthetic biology, biotechnology, or dual-use research
• Experience building and scaling threat detection systems or abuse monitoring programs
• Active Top Secret security clearance

About the Role

We are looking for a Technical Cyber Threat Investigator to join our Threat Intelligence team. In this role, you will be responsible for detecting, investigating, and disrupting the misuse of Anthropic's AI systems for malicious cyber operations. 

You will work at the intersection of AI safety and cybersecurity, conducting thorough investigations into potential misuse cases, developing novel detection techniques, and building robust defenses against emerging cyber threats in the rapidly evolving landscape of AI-enabled risks. Your work will directly protect the broader ecosystem from sophisticated threat actors who seek to leverage AI technology for harm.

Important context: In this position you may be exposed to explicit content spanning a range of topics, including those of a sexual, violent, or psychologically disturbing nature. This role may require responding to escalations during weekends and holidays.

Responsibilities

• Detect and investigate attempts to misuse Anthropic's AI systems for cyber operations, including influence operations, malware development, social engineering, and other adversarial activities
• Develop abuse signals and tracking strategies to proactively detect sophisticated threat actors across our platform
• Create actionable intelligence reports on new attack vectors, vulnerabilities, and threat actor TTPs targeting LLM systems
• Conduct cross-platform threat analysis grounded in real threat actor behavior, using open-source research, dark web monitoring, and internal data
• Utilize investigation findings to implement systematic improvements to our safety approach and mitigate harm at scale
• Study trends internally and in the broader ecosystem to anticipate how AI systems could be misused, generating and publishing reports
• Build and maintain relationships with external threat intelligence partners, information sharing communities, and government stakeholders
• Work cross-functionally to build out our threat intelligence program, establishing processes, tools, and best practices

You may be a good fit if you

• Have demonstrated proficiency in SQL and Python for data analysis and threat detection
• Have experience with large language models and understanding of how AI technology could be misused for cyber threats
• Have subject matter expertise in abusive user behavior detection, such as influence operations, coordinated inauthentic behavior, or cyber threat intelligence
• Have experience tracking threat actors across surface, deep, and dark web environments
• Can derive insights from large datasets to make key decisions and recommendations
• Have experience with threat actor profiling and utilizing threat intelligence frameworks (MITRE ATT&CK, etc.)
• Have strong project management skills and ability to build processes from the ground up
• Possess excellent communication skills to collaborate with cross-functional teams and present to leadership

Strong candidates may also have

• Experience working with government agencies or in regulated environments
• Background in AI safety, machine learning security, or technology abuse investigation
• Experience building and scaling threat detection systems or abuse monitoring programs
• Active Top Secret security clearance

Deadline to apply

None. Applications will be reviewed on a rolling basis.

About the Role:

We are looking for a cybersecurity expert to lead our efforts to prevent AI misuse in the cyber domain. As a Cyber Harms Technical Policy Manager, you will lead a team applying deep technical expertise to inform the design of safety systems that detect harmful cyber behaviors and prevent misuse by sophisticated threat actors. Working closely with Research Engineers who build these safety systems, you and your team will provide the critical cybersecurity domain knowledge needed to ensure our safeguards are effective against real-world threats. You will be at the forefront of defining what responsible AI safety looks like in the cybersecurity domain, working across research, policy, and engineering to translate complex cyber threat concepts into concrete technical safeguards and actionable policies. This is a unique opportunity to shape how frontier AI models handle dual-use cybersecurity knowledge—balancing the tremendous potential of AI to advance legitimate security research and defensive capabilities while preventing misuse by malicious actors.

In this role, you will:

• Lead and grow a team of technical specialists focused on cyber threat modeling and evaluation frameworks
• Design and oversee execution of capability evaluations ("evals") to assess the cyber-relevant capabilities of new models
• Create comprehensive cyber threat models, including attack vectors, exploit chains, precursor identification, and weaponization techniques
• Develop and iterate on usage policies that govern responsible use of our models for emerging capabilities and use cases related to cyber harms
• Serve as the primary domain expert on cyber harms, advising cross-functional teams on threat landscapes and mitigation strategies
• Collaborate closely with internal and external threat modeling experts to develop training data for safety systems, and with ML engineers to train these systems, optimizing for both robustness against adversarial attacks and low false-positive rates for legitimate security researchers
• Analyze safety system performance in traffic, identifying gaps and proposing improvements
• Conduct regular reviews of existing policies and enforcement systems to identify and address gaps and ambiguities related to cybersecurity risks
• Develop rigorous stress-testing of safeguards against evolving cyber threats and product surfaces
• Partner with Research, Product, Policy, Security Team, and Frontier Red Team to ensure cybersecurity safety is embedded throughout the model development lifecycle
• Translate cybersecurity domain knowledge into actionable safety requirements and clearly articulated policies
• Contribute to external communications, including model cards, blog posts, and policy documents related to cybersecurity safety
• Monitor emerging technologies and threat landscapes for their potential to contribute to new risks and mitigation strategies, and strategically address these
• Mentor and develop team members, fostering a culture of technical excellence and responsible AI development

You may be a good fit if you have:

• An M.S. or PhD in Computer Science, Cybersecurity, or a related technical field, OR equivalent professional experience in offensive or defensive cybersecurity
• 5+ years of hands-on experience in cybersecurity, with deep expertise in areas such as vulnerability research, exploit development, network security, malware analysis, or penetration testing
• 2+ years of experience managing technical teams or leading complex technical projects with multiple stakeholders
• Experience in scientific computing and data analysis, with proficiency in programming (Python preferred)
• Deep expertise in modern cybersecurity, including both offensive techniques (vulnerability research, exploit development, penetration testing, malware analysis) and defensive measures (detection, monitoring, incident response)
• Demonstrated ability to create threat models and translate technical cyber risks into policy frameworks
• Familiarity with responsible disclosure practices, vulnerability coordination, and cybersecurity frameworks (e.g., MITRE ATT&CK, NIST Cybersecurity Framework, CWE/CVE systems)
• Strong analytical and writing skills, with the ability to navigate ambiguity and explain complex technical concepts to non-technical stakeholders
• Experience developing policies or guidelines at scale, balancing safety concerns with enabling legitimate use cases
• A passion for learning new skills and an ability to rapidly adapt to changing techniques and technologies
• Comfort working in a fast-paced environment where priorities may shift as AI capabilities evolve
• Track record of translating specialized technical knowledge into actionable safety policies or enforcement guidelines

Preferred Qualifications:

• Background in AI/ML systems, particularly experience with large language models
• Experience developing ML-based security systems or adversarial ML research
• Experience working with defense, intelligence, or security organizations (e.g., NSA, CISA, national labs, security contractors)
• Published security research, disclosed vulnerabilities, or participated in bug bounty programs
• Understanding of Trust & Safety operations and content moderation at scale
• Certifications such as OSCP, OSCE, GXPN, or equivalent demonstrating technical depth
• Understanding of dual-use security research concerns and ethical considerations in AI safety

About the Role

Anthropic's Safeguards team is responsible for enforcing our policies, protecting users, and ensuring our platform is not misused. As a Safeguards Enforcement Analyst focused on Safety Evaluations, you'll play a central role in ensuring our models meet safety and policy standards before and after launch. You'll run and monitor evaluations, drive mitigations when issues surface, coordinate the creation of new evals, and help build the processes and documentation that allow the team to scale this work over time.

This role requires someone who is detail-oriented, comfortable navigating ambiguity, and capable of coordinating across teams to break new ground and drive work to completion. This work is deeply cross-functional — you'll partner closely with policy experts, Safeguards engineering teams, and many other stakeholders throughout the organization to ensure our evaluations are comprehensive and current, and that findings translate into meaningful improvements to model behavior.

Responsibilities

• Support model launch readiness by running evaluations, monitoring and interpreting results, and surfacing regressions or unexpected behavior changes to relevant stakeholders
• Partner closely with policy and domain experts throughout the evaluation lifecycle — from identifying risks and scoping the right evaluation approach, to coordinating creation of new evals and ensuring existing ones remain current with evolving policies, threat vectors, and model capabilities
• Work with cross-functional stakeholders to help manage evaluation outcomes, including interpreting results and driving mitigations where needed
• Think strategically about eval quality to build processes and eval paradigms that keep evaluations unsaturated, high-signal, and insightful as models improve
• Build out processes and frameworks for creating product-specific evaluations as Anthropic's product surface area expands
• Help design and scope tooling improvements that accommodate evolving eval needs and expand self-serve eval creation and iteration for non-technical users
• Write and maintain rigorous documentation for evaluation creation, execution, and interpretation as the team builds out eval tooling and processes

You may be a good fit if you:

• Have experience in trust and safety, content operations, policy enforcement, or a related operational role at a technology company
• Thrive in ambiguous, fast-moving environments — you're energized rather than frustrated when the path forward isn't clearly defined and you need to figure it out as you go
• Have experience building processes, workflows, or programs from scratch (zero-to-one work), not just maintaining existing ones
• Have strong program management instincts, naturally creating structure around complex, multi-stakeholder efforts by tracking timelines, dependencies, and deliverables to keep work on track
• Are eager to expand your technical toolkit, including adopting internal tools and AI-assisted workflows (e.g., Claude Code) to accelerate your work
• Can manage multiple concurrent workstreams across different domain areas without losing track of details — strong prioritization and context-switching are essential when deadlines and priorities shift quickly
• Are a strong generalist comfortable moving fluidly across different types of work and switching contexts throughout the day
• Are comfortable making judgment calls with incomplete information and escalating appropriately when needed
• Communicate clearly and concisely, both in writing and cross-functionally

Strong candidates may also have:

• Experience operating under tight, high-stakes timelines — such as product launch cycles, incident response, or regulatory deadlines — where information and priorities can shift with little notice
• Experience coordinating across engineering, policy, and product teams to translate findings into concrete action
• Experience building and maintaining SOPs, runbooks, and operational documentation in fast-changing environments
• Proficiency with data tools (SQL, dashboards, spreadsheets) sufficient to maintain and improve workflows
• Comfort working with sensitive content areas as part of eval creation or enforcement review responsibilities