Member of Technical Staff, Statistical Genetics

Location: SF Bay Area
Type: Full-time

About Radical Numerics

Radical Numerics is an AI research lab building general biological intelligence. Our mission is to master the language of life, and our purpose is to reduce human suffering.

Our team created Evo, and started the field of generative genomics. Our work was featured on the cover of Science, and presented by our CEO on the main stage of TED2025. Evo was used to create the first AI gene therapy tool CRISPR-Cas9, and the first AI whole genome from scratch. Evo 2, featured in Nature, is the largest fully open source AI project across any domain.

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We’ve redesigned the foundation model training stack to turn the world’s raw scientific data (e.g. biological sequences, experiments, and physical processes), into intelligible, generative models that can expand and accelerate what humanity can understand, design, and cure.

We are building a new type of AI research lab, driving both the frontier of biological AI for human health, and building the systems to defend against its potential misuse. The same generative breakthroughs that enable life saving cures also lowers the barrier to creating engineered threats and AI-generated bioweapons. We believe these forces are inseparable. Radical Numerics was founded to develop both the power to design and the responsibility to defend.

About the Role

As a Member of Technical Staff focused on statistical genetics, you will help us turn genetic association data into a rigorous substrate for biological foundation models. You will work with diverse data streams from GWAS, QTLs, variant annotation, biobank-scale phenotypes, and functional genomics to ask a central question: do our models understand the structure of genetic variation and its relationship to molecular and organismal traits?

This role is part data architect, part methods scientist, and part model evaluator. You will collaborate closely with AI engineers and computational biologists to design datasets, benchmarks, and analyses that make models performant and scientifically interpretable.

What You'll Do

• Build and evaluate large-scale statistical genetics resources for model training and assessment, including GWAS summary statistics, QTL maps, fine-mapping results, variant annotations, haplotypes, population reference panels, and biobank-scale phenotype data.
• Design benchmarks that test whether models capture genetic architecture: linkage disequilibrium, ancestry, constraint, polygenicity, pleiotropy, regulatory effects, rare variant burden, and cross-population generalization.
• Partner with AI/ML engineers to analyze model behavior on variant effect prediction, disease association, genotype-to-phenotype prediction, regulatory region interpretation.
• Develop practical standards for genetic data provenance, QC, leakage prevention, population bias assessment, privacy, consent, and responsible use of human genetic data.

What We're Looking For

• PhD in statistical genetics, human genetics, computational biology, biostatistics, or a related field, OR substantial industry experience working with population-scale genetic data.
• Deep working knowledge of concepts and methods in statistical genetics: GWAS, LD, ancestry/population structure, heritability, fine-mapping, QTL mapping, rare variant analysis, polygenic risk, and variant annotation.
• Experience with large genetic resources such as UK Biobank, All of Us, TOPMed, gnomAD, GTEx, FinnGen, ENCODE, or similar datasets.
• Strong computational fluency with Python, HPC, and modern genomic data tooling.
• Clear communicator who can bridge scientific context with engineering teams and partner organizations.
• Curiosity and resilience when tackling open-ended scientific challenges.

Nice to Have

• Experience integrating genetics with functional genomics, single-cell data, perturbational screens, proteomics, metabolomics, imaging, or clinical phenotypes.
• Familiarity with ML for genomics, including sequence models, variant effect predictors, regulatory models, multimodal models, or biological foundation models.
• Experience with colocalization, Mendelian randomization, TWAS, causal inference, cross-ancestry genetics, admixed populations, or privacy-preserving genomic analysis.
• A track record of building reproducible pipelines, shared resources, open datasets, or benchmarking frameworks used by other scientists.

Why Radical Numerics

• Help build biological world models that understand human genetic variation, not just reference sequences.
• Work on foundational problems at the intersection of statistical genetics, machine learning, and large-scale biological data infrastructure.
• Join a collaborative team spanning AI labs, biotechs, hospital systems, and research institutes, with competitive compensation, comprehensive benefits, and support for continual learning.

Senior Engineering Manager

Location: SF Bay Area or Tokyo, Japan
Type: Full-time

About Radical Numerics

Radical Numerics is an AI research lab building general biological intelligence. Our mission is to master the language of life, and our purpose is to reduce human suffering.

Our team created Evo, and started the field of generative genomics. Our work was featured on the cover of Science, and presented by our CEO on the main stage of TED2025. Evo was used to create the first AI gene therapy tool CRISPR-Cas9, and the first AI whole genome from scratch. Evo 2, featured in Nature, is the largest fully open source AI project across any domain.

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We’ve redesigned the foundation model training stack to turn the world’s raw scientific data (e.g. biological sequences, experiments, and physical processes), into intelligible, generative models that can expand and accelerate what humanity can understand, design, and cure.

We are building a new type of AI research lab, driving both the frontier of biological AI for human health, and building the systems to defend against its potential misuse. The same generative breakthroughs that enable life saving cures also lowers the barrier to creating engineered threats and AI-generated bioweapons. We believe these forces are inseparable. Radical Numerics was founded to develop both the power to design and the responsibility to defend.

About the Role

We’re hiring a Senior Engineering Manager to lead a team working across ML infrastructure, training systems, and research engineering in support of biological world models.

This is a hybrid leadership role for someone who can grow strong engineers, raise the quality bar, and help teams execute on technically ambitious work. You will partner closely with technical leads, researchers, and company leadership to set direction for critical systems and translate that direction into reliable, high-velocity execution.

This role combines management with technical depth. You should be comfortable leading senior engineers, helping shape system architectures and stepping into complex technical discussions when needed. The ideal candidate has experience in high-performance systems, distributed training, data infrastructure, or other environments where research velocity depends on strong engineering foundations.

What You’ll Do

• Build and lead a strong engineering team. Hire selectively, mentor deeply, and maintain a high bar for execution and code quality.
• Own core infrastructure. Drive development of systems for large-scale model training and experimentation—training/inference, data pipelines, evals, and internal tools.
• Set technical direction. Make clear architectural tradeoffs (performance vs. speed vs. flexibility), and guide where to invest vs. keep things simple.
• Accelerate research. Improve reproducibility, observability, and debugging to enable faster iteration and more reliable experiments.
• Stay close to the work. Partner tightly with researchers and step into design, debugging, and ambiguous problems when needed.

What We’re Looking For

• Track record leading engineering teams in technically demanding environments, ideally where infrastructure and research are closely linked.
• Experience managing senior engineers and enabling high-autonomy teams.
• Strong background in distributed systems, data systems, developer platforms, or similarly complex technical areas.
• Ability to work credibly with researchers and senior engineers on system architectures, prioritization, and execution.
• Strong technical judgment, especially around tradeoffs, sequencing, and operating under ambiguity.
• Comfortable staying close to the work, including going deep on design or debugging when needed.
• Excellent communication skills and the ability to align stakeholders across engineering, research, and science.
• High standards for rigor, speed, and practical decision-making.

Nice to Have

• Familiarity with large-scale pretraining and model serving workflows, multimodal data, and research platforms.
• Experience in companies or teams where engineering supported frontier research or fast-moving technical R&D.
• Track record of hiring and developing engineering leaders in addition to individual contributors.

Why Radical Numerics

• Help build the multimodal biological world models needed for rapid detection, response, and countermeasures across global health. 
• Work on foundational engineering problems at the intersection of AI systems, large-scale model training, and biology. 
• Join a collaborative culture that values rigor, creativity, and cross-disciplinary partnership across AI labs, biotechs, hospital systems, and research institutes. 
• Competitive compensation, comprehensive benefits, and support for continual learning.

Chief of Staff

Location: SF Bay Area
Type: Full-time

About Radical Numerics

Radical Numerics is an AI research lab building general biological intelligence. Our mission is to master the language of life, and our purpose is to reduce human suffering.

Our team created Evo, and started the field of generative genomics. Our work was featured on the cover of Science, and presented by our CEO on the main stage of TED2025. Evo was used to create the first AI gene therapy tool CRISPR-Cas9, and the first AI whole genome from scratch. Evo 2, featured in Nature, is the largest fully open source AI project across any domain.

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We’ve redesigned the foundation model training stack to turn the world’s raw scientific data (e.g. biological sequences, experiments, and physical processes), into intelligible, generative models that can expand and accelerate what humanity can understand, design, and cure.

We are building a new type of AI research lab, driving both the frontier of biological AI for human health, and building the systems to defend against its potential misuse. The same generative breakthroughs that enable life saving cures also lowers the barrier to creating engineered threats and AI-generated bioweapons. We believe these forces are inseparable. Radical Numerics was founded to develop both the power to design and the responsibility to defend.

About the Role

As Chief of Staff, you will operate at the center of Radical Numerics, partnering directly with the CEO and leadership team to drive the company’s most critical priorities. This is a high-leverage, execution-focused role designed for someone who can bring structure to ambiguity, accelerate decision-making, and ensure that the company operates at the pace of its ambition.

You will work across the entire org, from operations, commercial and product, and owning key initiatives end-to-end. You will help shape how the company scales: building the systems, processes, and communication loops that allow a frontier research lab to move quickly without losing rigor.

You will step into the highest-priority problems at any given moment, whether that’s preparing for investor conversations, structuring strategic partnerships with governments or biotech companies, refining our narrative, or helping stand up entirely new efforts like our biosecurity platform.

You will also serve as a force multiplier for the CEO—extending their reach, sharpening thinking, and ensuring follow-through across the organization. This requires strong judgment, high ownership, and the ability to operate across technical and non-technical domains.

The ideal candidate is deeply curious, highly adaptable, and motivated by the opportunity to help build a new kind of AI research lab, one that advances both the power to design biology and the systems to defend against its misuse.

What You'll Do

• Execute on the CEO and leadership team’s top priorities—translating direction into concrete plans and outcomes
• Own operational workflows across the company, including legal coordination, commercial operations, and internal processes
• Manage execution for fundraising processes: preparing materials, coordinating diligence, and maintaining investor pipelines
• Support commercial operations, including preparing proposals, contracts, and offer letters
• Build and maintain internal systems that keep the company running efficiently (tracking, reporting, communication cadence)
• Prepare high-quality presentations, documents, and analyses for internal and external use
• Coordinate across teams to ensure alignment and follow-through on key initiatives
• Identify execution gaps and step in to resolve them quickly and reliably

What We're Looking For

• 1–4 years of experience in a high-performance, execution-oriented environment (e.g., McKinsey & Company, Goldman Sachs, high-growth startups, or similar)
• Exceptional executor. You reliably deliver high-quality work quickly and with minimal oversight
• Strong attention to detail and operational rigor; you do not let things slip
• Comfortable operating in a support role to senior leadership, with a focus on enabling others to move faster
• Highly organized, able to manage multiple work streams and deadlines simultaneously
• Clear and concise communicator, especially in written materials and presentations
• Low ego, high ownership. You prioritize team success over personal positioning
• Strong judgment and discretion when handling sensitive information

Nice to Have

• Experience supporting founders or executives in a Chief of Staff, business analyst, or operations role
• Exposure to legal processes (contracts, financing docs) or fundraising workflows
• Experience with financial modeling, reporting, or investor materials
• Familiarity with startup operations or early-stage company environments
• Interest in AI, biology, or working at the frontier of science and technology

Member of Technical Staff, Biosecurity

Location: SF Bay Area
Type: Full-time

About Radical Numerics

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast biological sequence, structure, and image datasets so that biological world models become a reality. Our team introduced hybrid architectures that unlocked million-token context windows, enabling work toward AI-designed whole genomes and real gene-editing tools.

We believe biology will be the most impactful and consequential application of AI—and that advancing capabilities must go hand-in-hand with advancing safety and biosecurity. The same systems that design biology must also help defend against it. This role is focused on building and deploying the technical systems that make biosecurity real.

About the Role

As a Member of Technical Staff, Biosecurity at Radical Numerics, you will lead the design, evaluation, and deployment of biosecurity systems for biological foundation models. You will build evaluation frameworks, define safety architecture, and work with government and external partners to translate technical capabilities into real-world biosecurity infrastructure.

This role blends research and engineering. You should be excited to move fluidly between technical depth and external engagement: understanding model behavior, building red-teaming and evaluation pipelines, designing system-level safeguards, and working with stakeholders to deploy biosecurity systems at scale.

What You'll Do

• Design and run biosecurity evaluations. Develop evaluation frameworks for biological foundation models covering sequence generation risk, synthesis screening evasion, and capability assessment across genomics, proteins, and multimodal systems. Build red-teaming pipelines and define benchmarks that measure real-world risk and misuse potential.
• Work directly with models and data. Prototype pipelines for pathogen detection, sequence classification, anomaly detection, and risk scoring of biological sequences or designs. Collaborate with research teams to understand model behavior, identify dangerous capabilities early, and inform model design with safety constraints.
• Define safety architecture. Help design system-level safeguards including access controls, gating, monitoring, human-in-the-loop review, and deployment constraints for sensitive capabilities. Contribute to internal safety standards and release policies.
• Bridge to real-world biosecurity systems. Translate technical capabilities into deployable systems such as biosurveillance platforms, sequence screening tools, and rapid detection and response pipelines. Work with government and partners to align systems with real-world workflows.
• Drive partnerships and external engagement. Engage with government agencies, help shape joint technical programs and pilots, and communicate model capabilities, risks, and mitigations clearly to stakeholders.
• Identify new opportunities. Discover product and platform opportunities in biosecurity, help define Radical Numerics' role in global biological risk infrastructure, and operate with high ownership in a fast-moving, ambiguous environment.

What We're Looking For

• Strong technical background in at least one of: machine learning and AI systems (especially large models), computational biology and bioinformatics, or biosecurity and biodefense with technical depth.
• Ability to reason concretely about what biological AI systems can and cannot do, how those capabilities translate into real-world risks, and how to measure and mitigate those risks.
• Experience building or working with ML systems, or strong computational biology experience.
• Ability to design evaluations, benchmarks, or experimental frameworks for biological data, including genomic sequences, pathogens, protein data, or multi-omics.
• Strong intuition for failure modes, adversarial behavior, and misuse risks, with the ability to translate ambiguous risks into concrete technical work.
• High agency: defines problems, runs with them, and ships.
• Excellent written and verbal communication skills, especially the ability to engage credibly with government, labs, and policy stakeholders and translate technical systems into clear narratives.

Nice to Have

• Experience with pathogen genomics, biosurveillance, or DNA synthesis screening.
• Background in AI safety, red-teaming, or model evaluations.
• Familiarity with hybrid systems such as BLAST + ML or retrieval + generation pipelines.
• Experience with models like Evo, ESM, AlphaFold, or genomic foundation models.
• Background in biodefense, intelligence, or global health security.
• Existing network across government, national labs, or global health organizations.

Why Radical Numerics

• Help build the multimodal biological world models needed for rapid detection, response, and countermeasures across global health.
• Work directly on frontier biological AI systems and define how they are evaluated, controlled, and deployed.
• Help shape global infrastructure for biological risk detection and response.

Member of Technical Staff, Computational Biology

Location: SF Bay Area
Type: Full-time

About Radical Numerics  

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast multimodal biological datasets so that biological world models become a reality. Our team introduced the first hybrid architectures that unlocked million-token context windows, enabling the first AI-designed whole genomes and real gene-editing tools.

About the Role  

As a science-focused Member of Technical Staff, you will curate the multimodal biological datasets that power our models, analyze model behavior, and ensure our model outputs meet rigorous scientific standards. You'll co-develop benchmarks, filters, and validation pipelines with engineering peers so biological world models remain trustworthy and actionable.

What You'll Do 

• Source, normalize, and steward large-scale genomic, epigenomic, transcriptomic, proteomic, and imaging datasets with rigorous metadata and provenance.  
• Build evaluation suites and benchmarks that stress-test generative biological models across modalities and tasks.
• Partner with AI engineers to analyze model outputs, run ablations, and surface insights that guide future architecture and training improvements.  
• Integrate new datasets and annotations from external collaborators while maintaining compliance, privacy, and ethical standards.  
• Communicate findings and best practices across Radical Numerics so teams can trust and act on model results.

What We're Looking For

• PhD in genetics, computational biology, or a related field, OR demonstrated experience in biotech with a strong track record of impact over 3+ years.
• Proven experience curating, harmonizing, and analyzing large biological datasets (e.g., genomics, single-cell, spatial, or imaging).
• Fluency with Python, data tooling, and reproducible workflows (git, notebooks, containers).  
• Ability to interrogate model outputs, debug unexpected behaviors, and translate findings into actionable recommendations.
• Clear communicator who can bridge scientific context with engineering teams and partner organizations.
• Curiosity and resilience when tackling open-ended scientific challenges.

Nice to Have 

• Familiarity with generative model evaluation, red-teaming, or safety analysis in scientific domains.
• Experience with statistical validation, quality control, or benchmarking for scientific or ML systems.
• Experience building benchmarking frameworks or open datasets that became community standards.  
• Contributions to shared analytics tooling or reproducible research pipelines.

Why Radical Numerics 

• Help produce the multimodal biological world models that will power rapid detection, response, and countermeasures across global health.  
• Collaborative culture that values rigor, creativity, and cross-disciplinary partnership across AI labs, biotechs, hospital systems, and national research institutes.  
• Competitive compensation, comprehensive benefits, and support for continual learning.

How to Apply  

Send your resume, a brief note on why Radical Numerics resonates with you, and examples of relevant public codebases you’ve built. We review applications on a rolling basis.

Member of Technical Staff, Backend Engineering

Location: SF Bay Area or Tokyo, Japan
Type: Full-time

About Radical Numerics

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast biological sequence, structure, and image datasets so that biological world models become a reality. Our team introduced hybrid architectures for million-token context windows, enabling work toward AI-designed whole genomes and gene-editing tools.

We believe the next generation of biological foundation models will require not only better models and training systems, but also robust backend infrastructure that makes those systems usable in practice. This role focuses on the backend services and APIs that connect our research platform to internal tools, external products, and real-world scientific workflows.

About the Role

As a Member of Technical Staff, Backend Engineering at Radical Numerics, you will design, build, and operate backend services that power APIs and platform capabilities across the company. You will help create the systems that make model capabilities accessible, reliable, and easy to integrate, whether for internal researchers, external users, or downstream scientific applications.

This is a hands-on role for someone who wants to own backend systems end-to-end. You should be excited to move from API design to implementation to deployment to observability, while working closely with researchers and product-minded engineers to ensure the systems we build are useful, scalable, and maintainable. 

What You’ll Do

• Build backend services for APIs and platform products. Design and implement backend systems that expose model capabilities, data services, and internal platform functionality through clean, reliable APIs.
• Own services end-to-end. Take backend systems from design docs through implementation, testing, deployment, monitoring, and iteration based on real usage patterns and operational feedback.
• Design for scalability and reliability. Build services that can handle growing traffic, large datasets, and demanding internal workloads while maintaining correctness, low latency, and operational robustness.
• Develop developer-friendly APIs and abstractions. Create clear, well-documented interfaces that make it easy for internal teams and external users to build on top of our systems. 
• Improve backend architecture and platform foundations. Analyze existing systems, identify bottlenecks, and improve the maintainability, fault tolerance, and self-serve usability of our backend stack.
• Work closely with research and product teams. Partner with model researchers, infrastructure engineers, and application teams to understand requirements and translate them into backend systems that support real workflows.
• Build observability and operational tooling. Develop logging, monitoring, tracing, and alerting systems that help us understand service behavior in production and respond quickly when things go wrong.

What We’re Looking For

• Strong track record building production backend systems, distributed systems, APIs, or data services.
• Proficiency in at least one backend language such as Python, Go, Java, or Rust, along with strong software design fundamentals. 
• Experience designing and operating production APIs, including interface design, authentication, versioning, reliability, and monitoring.
• Ability to own services end-to-end: architecture, implementation, testing, deployment, and operational support. 
• Strong understanding of scalable systems design, including data modeling, concurrency, failure modes, and performance tradeoffs.
• Excellent written and verbal communication skills, especially the ability to collaborate across engineering, research, and scientific teams.

Nice to Have

• Experience with event-driven systems, streaming infrastructure, or workflow orchestration.
• Experience with SQL, OLTP/OLAP systems, or data platforms that support analytics or model-facing applications. 
• Experience building self-serve internal platforms, multi-tenant services, or control-plane-style systems. 
• Familiarity with ML or AI product infrastructure, including telemetry, metadata services, inference-facing APIs, or evaluation-related backend systems.
• Experience with security, governance, auditability, data retention, or privacy-aware backend design. 
• Background in distributed systems, infrastructure, computational biology, or another quantitative technical field.

Why Radical Numerics

• Help build the backend platform that makes multimodal biological world models usable in research and product settings.
• Work in an environment that combines distributed systems, model architecture, and numerics research with real biological applications.
• Join a collaborative culture that values rigor, creativity, and cross-disciplinary partnership across AI labs, biotechs, hospital systems, and research institutes.
• Competitive compensation, comprehensive benefits, and support for continual learning.

Head of Data Partnerships

Location: SF Bay Area
Type: Full-time

About Radical Numerics

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast multimodal biological datasets so that biological world models become a reality.

Our team introduced the first hybrid architectures that unlocked million-token context windows, enabling the first AI-designed whole genomes and real gene-editing tools.

About the Role

As the lead of Radical Numerics’ biological data discovery efforts, you will operate at the frontier of science, partnerships, and exploration. Your mission is to identify and unlock the world’s most valuable biological datasets, many of which are not publicly available and require trust, relationships, and persistence to access.

This role is part strategist, part explorer, and part dealmaker. You will work closely with our AI researchers and scientists to identify which datasets will have the greatest impact on training the next generation of biological world models. You will then travel globally to meet researchers, hospital systems, national biobanks, sequencing centers, and pharmaceutical partners face-to-face, building relationships that allow Radical Numerics to access these datasets. 

What You'll Do

Global data discovery

• Map the global landscape of biological datasets across genomics, epigenomics, transcriptomics, proteomics, metabolomics, imaging, and clinical data.
• Identify high-value datasets across pharma pipelines, national biobanks, hospital systems, sequencing centers, research institutes, and government repositories.

Relationship building

• Travel internationally to build trusted relationships with scientists, hospital administrators, sequencing labs, biotech companies, and government programs.
• Represent Radical Numerics in scientific and industry environments, establishing credibility and trust with institutions that control critical data assets.

Data acquisition strategy

• Work closely with internal scientists and ML engineers to understand which datasets most improve model capability.
• Evaluate dataset quality, scale, coverage, and modality diversity to prioritize acquisitions.

Negotiation and dealmaking

• Structure and negotiate agreements that unlock access to datasets while navigating regulatory, privacy, ethical, and IP considerations.
• Work alongside legal and compliance teams to close data-sharing and licensing agreements efficiently.

Pipeline development

• Build and maintain a global pipeline of potential data partnerships.
• Identify emerging programs, consortia, and initiatives where early engagement could secure long-term data access.

What We're Looking For

• Strong domain knowledge in genomics, sequencing, and imaging technologies, with intuition for what makes a dataset valuable for training large-scale biological models.
• Proven ability to build relationships across biotech, pharma, hospitals, research institutes, or global scientific networks.
• Experience securing access to datasets, partnerships, or collaborations in life sciences or healthcare.
• Excellent negotiation and communication skills with both scientific and business stakeholders.
• Comfort operating in ambiguous environments and navigating complex institutions to unlock opportunities.

Most importantly, we are looking for someone who is relentless in pursuing data: someone who will fly across the world to meet the people who control the datasets that will power the future of biological AI.

Nice to Have

• Prior roles in business development, partnerships, or data licensing in biotech or healthcare.
• Experience working with international research collaborations or large scientific consortia.
• Familiarity with regulatory environments around health data and genomics (HIPAA, GDPR, etc.).
• Prior academic or industry research experience with genomics or multi-omics datasets.

Member of Technical Staff, AI Bio

Location: SF Bay Area
Type: Full-time

About Radical Numerics

Radical Numerics is an AI lab bringing the rigor of distributed systems, bioinformatics, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast multimodal biological datasets so that biological world models become a reality. Our team introduced the first hybrid architectures that unlocked million-token context windows, enabling the first AI-designed whole genomes and real gene-editing tools.

About the Role

We are seeking research scientists and engineers working at the intersection of machine learning and biological modeling to develop frontier AI architectures for biological problems.

In this role, you will extend and adapt large model backbones—such as sequence and multimodal foundation models—to enable tasks across genomics, protein biology, and cellular systems. This includes designing post-training pipelines, domain adaptation strategies, and evaluation frameworks that enable state-of-the-art  ML frameworks  to reason over biological data.  You likely know the inner workings of frontier bio models such as AlphaFold, AlphaGenome, ESM, Evo, and thought about ways to improve, evaluate or apply them in novel ways.

You will collaborate with computational biologists to systems architecture researchers to translate advances in large-scale machine learning into capabilities for modeling biological systems, ranging from genome interpretation and regulatory modeling to multimodal cellular prediction and biological design.

What You'll Do

• Adapt frontier AI models to biological tasks through fine-tuning, post-training, adapters, and architectural modifications.
• Design and run experiments applying large models to problems in genomics, regulatory biology, protein biology, or cellular systems.
• Develop evaluation pipelines and benchmarks for biological tasks such as variant interpretation, gene regulation modeling, protein function prediction, and multimodal cellular modeling — and drive these capabilities toward grounded downstream biological impact.
• Design biologically meaningful data representations and modeling schemes across sequence, molecular, and multimodal data modalities.
• Analyze model behavior and run ablations to understand model reasoning and failure modes in biological contexts.
• Explore modern mechanistic interpretability pipelines and methods for biological discovery.
• Collaborate with model architecture teams to integrate biological capabilities into next-generation foundation models.
• Prototype new approaches for biological prediction and design using foundation models.

What We're Looking For

• Strong background and intuition in machine learning and deep learning across large-scale generative architectures, from autoregressive LLMs to diffusion models. 
• Experience adapting large models to new domains through fine-tuning, post-training, adapters, or architecture modifications.
• Experience applying ML models to biological data and challenging prediction tasks.
• Familiarity with molecular biology and biological data modalities, particularly genomics, gene regulation, protein biology, or cellular systems.
• Ability to design evaluation tasks and benchmarks that measure biological model capability beyond simple accuracy metrics, with a critical eye toward aligning computational outputs with actionable downstream applications.
• Strong Python and ML tooling experience (PyTorch or JAX, experiment management, distributed training).
• Ability to interpret biological datasets and translate biological questions into machine learning experiments.
• Mid-to-senior level experience building and deploying ML systems in research or production environments.

Nice to Have

• Experience with genomic or molecular sequence models (e.g., Evo, HyenaDNA, AlphaFold-style models, AlphaGenome-style tasks, virtual cell models).
• Background in ML for structural biology, or (bio)chemistry.
• Familiarity with multimodal biological modeling, including transcriptomics, epigenomics, chromatin accessibility, or spatial biology.
• Experience building robust evaluation suites for large AI systems.
• Experience scaling ML experiments across large GPU clusters.
• Research publications in ML for biology, chemistry, or related areas.

Why Radical Numerics

• We believe biology is the most impactful and consequential application of AI.  
• Join peers that are mission driven, and dedicated to creating radically innovative tech that will change the world and human health for the better.
• Work on frontier AI systems in a collaborative culture that values rigor, creativity, and cross-disciplinary partnership across AI labs, biotechs, hospital systems, and national research institutes.

Member of Technical Staff, Post-Training

Location: SF Bay Area or Tokyo, Japan
Type: Full-time

About Radical Numerics

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast biological sequence, structure, and image datasets so that biological world models become a reality. Our team introduced hybrid architectures for million-token context windows, enabling work toward AI-designed whole genomes and gene-editing tools. 

We believe the next generation of biological foundation models will require not only new and improved pretraining recipes, but also innovation on post-training: the work that turns a powerful base model into a system that is useful, steerable, robust, and scientifically productive. This role sits at that interface between fundamental research and practical engineering.

About the Role

As a Member of Technical Staff, Post-Training at Radical Numerics, you will develop the training and evaluation loops that shape biological world models after pretraining. You will work on the methods, data, and infrastructure required to improve model behavior on real scientific tasks: reasoning over long biological context, following complex objectives, making useful predictions, and interacting reliably with downstream tools and workflows.

This is a hands-on role for someone who wants to both build systems and deepen understanding. You should be excited to run careful experiments, question whether the metrics reflect reality, and translate empirical findings into better recipes, datasets, and productively used models.

What You’ll Do

• Develop and tune post-training recipes. Design and iterate on post-training stages, datasets, reward signals, and hyperparameters for biological world models. Study how choices in data mixtures, objective design, curriculum, and training schedules affect model behavior.
• Build evaluations that actually matter. Collaborate with the science team to develop and refine evaluation suites for biological reasoning, scientific usefulness, long-context behavior, robustness, and model reliability, and to identify when existing benchmarks stop being informative and should be replaced with better ones.
• Debug model behavior end-to-end. Investigate failure modes in training runs and model outputs, distinguish between signal and noise, and trace problems back to data, optimization, evaluation design, or systems issues.
• Work on preference- and feedback-driven learning. Explore methods such as preference modeling, reward modeling, synthetic feedback, or related post-training approaches that improve how models respond to scientific tasks and constraints.
• Improve data for post-training. Help define, curate, or generate high-quality post-training datasets, including expert-informed data, synthetic data, and task-specific examples grounded in biological workflows.
• Study scaling in post-training. Measure how performance changes with dataset size, recipe complexity, compute budget, and model family. Use those results to guide what we scale next and what new directions are worth exploring.
• Collaborate across research and engineering. Work closely with colleagues in training systems, architecture, and biology-facing research to ensure post-training methods are grounded in the realities of large-scale experimentation and downstream scientific use.

What We’re Looking For

• Strong track record in ML research or engineering, especially in frontier-model training, post-training, alignment, evaluation, data quality, or related areas.
• Proficiency in building production-quality software and research infrastructure, ideally in Python and PyTorch, with comfort debugging large-scale training workflows.
• Ability to design careful experiments, interpret ambiguous results, and separate real effects from artifacts, bugs, or benchmark overfitting.
• Excellent written and verbal communication skills, especially the ability to explain technical findings clearly across research, engineering, and scientific collaborators.
• Curiosity, rigor, and a bias toward iteration: you like improving systems by repeatedly tightening the loop between hypotheses, experiments, and insight.

Nice to Have

• Experience with RLHF, RLAIF, preference optimization, reward modeling, rejection sampling, or other post-training methods for large models.
• Experience designing or operating evaluation frameworks for model quality, reliability, safety, or scientific task performance.
• Familiarity with synthetic data generation, annotation workflows, or expert-in-the-loop data collection.
• Background in applied math, systems, computational biology, or another quantitative scientific field.
• Contributions to open-source ML systems, model tooling, or research infrastructure.

Why Radical Numerics

• Help build the post-training stack for multimodal biological world models that could materially improve how we detect, understand, and respond to problems in health and biology. 
• Work in an environment that combines distributed systems, model architecture, and numerics research with real biological applications. 
• Join a collaborative culture that values rigor, creativity, and cross-disciplinary partnership across AI labs, biotechs, hospital systems, and research institutes. 
• Competitive compensation, comprehensive benefits, and support for continual learning. 

Member of Technical Staff, Pre-Training Science

Location: SF Bay Area or Tokyo, Japan
Type: Full-time

About Radical Numerics

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast biological sequence, structure, and image datasets so that biological world models become a reality. Our team introduced hybrid architectures that unlocked million-token context windows, enabling work toward AI-designed whole genomes and real gene-editing tools. 

We believe that biological foundation models will require advances not only in systems and scale, but also in the science of pretraining itself: how models learn from diverse biological data, what objectives produce useful representations, and how training recipes evolve as models and datasets grow. This role is focused on that core scientific agenda.

About the Role

As a Member of Technical Staff, Pre-Training Science at Radical Numerics, you will work on the science of how biological world models learn during large-scale training. You will develop new pretraining methods, study scaling behavior, and design training recipes that improve efficiency, generalization, and downstream scientific usefulness.

This role blends research and engineering. You should be excited to move fluidly between theory and implementation: reading technical literature, proposing new hypotheses, running large-scale experiments, and writing high-performance code that turns ideas into measurable progress. 

What You’ll Do

• Research and develop new pretraining methodologies. Explore how biological world models learn from multi-modal data (eg, sequence, structure, and image data), and develop new objectives, training strategies, or architectural ideas that improve representation quality and downstream performance.
• Study scaling behavior. Investigate how training dynamics change with model size, data composition, context length, and compute budget. Use empirical results to inform scaling protocols and future research priorities.
• Design data curricula and sampling strategies. Build and refine mixtures, curricula, and sampling policies that improve learning efficiency, generalization, and robustness across biological modalities and tasks.
• Work on architecture, algorithms, and optimization. Evaluate ideas in model design, optimization, long-context learning, and training stability that make large-scale biological pretraining more effective.
• Run large-scale experiments rigorously. Design, execute, and analyze experiments with strong empirical discipline. Distinguish real effects from bugs, noise, or benchmark artifacts, and convert findings into better training recipes.
• Collaborate closely with infrastructure and data teams. Work across the stack to ensure large-scale experiments are reproducible, efficient, and instrumented well enough to support fast scientific iteration.
• Define evaluations for pretraining progress. Build and improve evaluation suites that measure representation quality, long-context behavior, transfer to downstream biological tasks, and scientific utility.

What We’re Looking For

• Strong track record in ML research or engineering, especially in large-scale model training, pretraining, representation learning, optimization, scaling laws, or related areas.
• Ability to design, run, and analyze experiments thoughtfully, with strong research judgment and empirical rigor. 
• Proficiency in Python and modern deep learning tooling such as PyTorch, plus comfort debugging distributed or high-performance training systems at scale. 
• Experience working in distributed or high-performance computing environments.
• Excellent written and verbal communication skills, especially the ability to explain complex technical findings clearly across engineering, research, and scientific collaborators.
• Intellectual curiosity and a bias toward experimentation, iteration, and continuous improvement. 

Nice to Have

• Experience training or analyzing frontier or foundation models.
• Strong grasp of probability, statistics, optimization, and ML fundamentals.
• Familiarity with curriculum learning, data selection, active learning, or data-quality methods for large-scale training.
• Experience designing or maintaining evaluation frameworks for large models.
• Contributions to open-source ML systems, datasets, or research tooling.
• Background in applied math, systems, computational biology, physics, mathematics, or another strongly quantitative field. 

Why Radical Numerics

• Help build the multimodal biological world models needed for rapid detection, response, and countermeasures across global health. 
• Work on fundamental questions in pretraining science while staying close to real scientific applications in biology.
• Join a collaborative culture that values rigor, creativity, and cross-disciplinary partnership across AI labs, biotechs, hospital systems, and research institutes. 
• Competitive compensation, comprehensive benefits, and support for continual learning. 

Member of Technical Staff, Infrastructure & Training Systems

Location: SF Bay Area or Tokyo, Japan
Type: Full-time

About Radical Numerics

Radical Numerics is an AI lab bringing the rigor of distributed systems, model architecture, and numerics research to the challenges of biology. We are building the infrastructure needed to unlock scaling on vast biological sequence, structure, and image datasets so that biological world models become a reality. Our team introduced hybrid architectures that unlocked million-token context windows, enabling work toward AI-designed whole genomes and real gene-editing tools. 

We believe biological world models will require not only strong research ideas, but exceptional training and inference systems: infrastructure that makes large-scale experimentation efficient, reproducible, and robust enough to support rapid scientific iteration. This role is focused on building that foundation.

About the Role

As a Member of Technical Staff, Infrastructure & Training Systems at Radical Numerics, you will design and build the systems that make large-scale model training possible across research and deployment workflows. You will work on distributed training, performance optimization, reusable internal frameworks, and the tooling that helps researchers move quickly without sacrificing reliability.

This role is ideal for someone who combines deep systems instincts with an interest in modern machine learning. You should care about how every layer of the stack affects research velocity: kernel performance, communication overhead, fault tolerance, observability, reproducibility, and the ergonomics of the training loop itself. 

What You’ll Do

• Design and scale distributed training systems. Build and optimize distributed training infrastructure for large-scale biological world models across large distributed compute systems, with a focus on performance, stability, and scalability. 
• Maximize throughput and hardware efficiency. Develop performance optimizations across the stack, including communication patterns, memory efficiency, custom kernels, compilation paths, and systems instrumentation, to ensure training compute is used effectively. 
• Build reusable training frameworks. Develop internal libraries, abstractions, and workflows that improve reproducibility, reliability, and scalability across new model architectures and training recipes. 
• Improve reliability under rapid iteration. Establish standards and mechanisms for robustness, maintainability, debugging, and safe deployment of fast-moving research infrastructure. That includes fault tolerance, checkpointing, monitoring, experiment hygiene, and incident analysis. 
• Collaborate across research and engineering. Partner closely with model researchers, training scientists, and data/infrastructure engineers to identify bottlenecks, unblock experiments, and design systems that support new scientific directions rather than constrain them. 
• Support new architectures and training paradigms. Adapt infrastructure to the needs of multimodal models, long-context training, and evolving model architectures, so the systems stack remains a research multiplier as model requirements change.

What We’re Looking For

• Strong engineering track record in distributed systems, high-performance ML infrastructure, training systems, or closely related areas.
• Proficiency in building performant, maintainable software in Python, PyTorch, Triton, CUDA, and C++. 
• Strong understanding of modern deep learning frameworks and their systems internals. 
• Ability to debug complex, multi-layered systems involving distributed training, memory/performance regressions, and reliability issues in large codebases. 
• Comfort working in a highly collaborative environment with researchers, engineers, and domain experts, with a bias toward initiative and execution. 
• Excellent written and verbal communication skills bridging technical and scientific domains. 

Nice to Have

• Experience with large-scale distributed training for frontier or foundation models.
• Contributions to open-source ML systems or infrastructure such as PyTorch, Torchtitan or Megatron-LM. 
• Familiarity with ML runtimes, compilers, numerics, communication libraries, and custom kernel development.
• Experience improving researcher productivity through infrastructure design, developer tooling, or workflow improvements. 
• Background in applied math, systems, computational biology, or related quantitative sciences. 

Why Radical Numerics

• Help build the computational foundation for multimodal biological world models aimed at rapid detection, response, and countermeasures across global health. 
• Work on systems problems at the frontier of distributed training, architecture, and numerics, in service of real biological applications. 
• Join a collaborative culture that values rigor, creativity, and cross-disciplinary partnership across AI labs, biotechs, hospital systems, and research institutes. 
• Competitive compensation, comprehensive benefits, and support for continual learning.