We are seeking a Staff or Principal Applied AI Researcher to join a fast growing team building an agent native search platform - the web access layer for AI systems.

You can think of this as Google for AI agents: a system designed for machines, not humans. We are building agentic search, where AI systems actively plan, retrieve, evaluate, and refine information rather than simply returning results. As AI becomes the primary interface to the web, this layer will replace the role of traditional search engines.

We are designing how AI agents - not humans - retrieve, evaluate, and reason over web data in real time, under strict latency and reliability constraints. This means solving retrieval and ranking under entirely new access patterns and at significant scale, with systems operating over constantly changing, unstructured data and serving tens of thousands of production workloads 24 by 7.

This role comes with ownership over key parts of our applied AI research direction and system design, with a strong expectation of defining new approaches and shipping measurable impact in production.

What you'll work on:

• Designing agent native retrieval systems optimised for machine consumption rather than human search UX
• Building systems where LLMs iteratively plan, query, refine, and reason over results
• Developing ranking and retrieval approaches for multi step, agent driven workflows under real world constraints

Your responsibilites:

• Drive applied research and technical direction across retrieval and ranking systems
• Design and evolve multi stage retrieval architectures (query understanding, rewriting, reranking, iterative retrieval)
• Develop methods for grounding LLMs in real time web data at scale
• Define and implement new evaluation paradigms and metrics for agentic systems, where correctness is not reducible to clicks
• Lead experimentation on modern retrieval approaches (embeddings, hybrid search, reranking) and bring them into production
• Analyse trade-offs across relevance, latency, and cost at scale
• Work closely with engineering to deploy systems in high throughput, low latency environments
• Own ambiguous problems end to end and contribute to product and research direction
• Mentor engineers and help raise the technical bar of the team

Must haves:

• 8+ years of experience in applied AI, ML, or software engineering
• Proven track record of shipping ML or AI systems to production at scale
• Deep experience with search, retrieval, ranking, recommendation systems, or assistants
• Strong understanding of modern deep learning, especially transformers and embeddings
• Experience with LLM integrated or knowledge intensive systems
• Experience designing evaluation frameworks and metrics for ML systems
• Strong programming skills in Python and at least one of Go, C++, or similar
• Ability to operate in a fast moving, product driven environment with high ownership and autonomy

Nice to haves

• Experience with large scale search or recommendation systems
• Background in agentic AI systems (agents, tool use, autonomous workflows)
• Experience with RAG, multi step retrieval, or tool use
• Publications, open source, or similar signals of technical depth and impact

The role

In a rapidly evolving world, trust in AI depends on AI agents being grounded in fresh, verified real-world data. Search is the foundation that makes this possible. In this role, you will define what quality means for a search system built for AI agents from day one.

In this position, your responsibility will be to

• Own search-related quality metrics end-to-end: from definition and computation to evolution and transition to next-generation metrics.
• Design and reason about analytics architecture across the full stack: runtime behaviour → data pipelines → metrics → dashboards.
• Develop and maintain analytics pipelines and tooling using Python.
• Translate product, user, and technical requirements into meaningful, actionable metrics.
• Challenge existing assumptions about quality and push for better, more reliable measurement.
• Work closely with product managers, engineers, and stakeholders to align analytics with system behavior and business goals.
• Debug metric anomalies, investigate quality regressions, and propose data-driven improvements.

We expect you to have

• Senior-level experience solving search or search-adjacent analytical problems.
• Strong exposure to quality metrics in at least one of the following areas:
  • search relevance (web, geo, product, offers),
  • ranking and freshness,
  • ads quality or feed ranking.
• Ability to think end-to-end across users, products, and technology, not just individual metrics.
• Solid foundation in mathematical statistics.
• Strong Python skills and a hands-on engineering mindset.
• Experience operating in ambiguous environments and driving solutions independently.
• Clear analytical judgment: understanding why a metric exists, how it evolves, and when it should be retired.
• Strong communication skills and the ability to align product, engineering, and client perspectives.

About Tavily Team

Tavily team is building the infrastructure layer for agentic web interaction at scale. Our API is designed from the ground up to power Retrieval-Augmented Generation (RAG) and real-time reasoning in AI systems. By connecting LLMs to high-quality, trustworthy web content, we help developers build agents that are not only intelligent - but also informed.

We work with some of the most innovative teams in AI - from small startups shaping the ecosystem to the largest enterprises deploying AI at scale. Whether it’s powering sales assistants, research copilots, or internal knowledge tools, we’re the missing link between LLMs and the real world.

The Role: Senior Backend Engineer (Tavily)

We're looking for a Software Engineer to join our core engineering team and help build the infrastructure behind one of the fastest-growing AI APIs. You'll work on systems that handle massive scale across a distributed microservices architecture running on AWS. You'll ship fast, take ownership of critical systems, and solve hard infrastructure problems as we grow.

This is a great role for an engineer who loves building ambitious systems from scratch, and wants to tackle the kind of scale and complexity challenges typically reserved for much larger companies.

What You’ll Do

• Design and build high-performance distributed systems

• Design and implement backend infrastructure and API endpoints

• Build and optimize real-time data pipelines that process billions of events per day across distributed queues and stream processors

• Improve performance, monitoring, and reliability across the stack

• Own core systems and contribute to key architectural decisions

• Help shape a strong engineering culture focused on velocity and quality

What You Bring

• 5 years of professional software engineering experience

• Strong backend development skills

• Proven experience designing and operating large-scale, distributed systems, with a solid understanding of API design, reliability, and performance at scale

• Hands-on expertise with AWS infrastructure and cloud-native services, bringing practical knowledge of deploying and managing services in real-world environments

• Comfortable in a fast-paced startup environment with lots of ownership

• Strong sense of ownership and accountability over outcomes

• Curiosity about LLMs, retrieval and the future of AI systems, with a drive to stay at the forefront of new technology

• Based in Tel-Aviv or open to relocating

Nice To Have

• Familiarity with DevOps practices, including CI/CD pipelines, infrastructure as code, Kubernetes orchestration, and modern monitoring tools

We are seeking a Senior Applied ML Engineer to join a fast-growing team building an agent-native search platform for AI systems, the emerging web access layer for AI. You will develop and deploy machine learning models that power retrieval, ranking, and indexing at scale, helping AI systems access fresh, reliable information in real time. This is a high-impact role working on a production system used 24x7, tackling challenges comparable to large-scale web search.

Your responsibilities:

• Design, train, and deploy ML models for retrieval, reranking, and search relevance in production
• Build and optimise embedding-based indexing and large-scale retrieval systems
• Develop models supporting crawling, data selection, and content understanding
• Define and improve quality metrics for agent-native search and build evaluation pipelines
• Work on systems operating at very large scale, including high-throughput query workloads
• Collaborate closely with engineering teams to integrate ML models into production services
• Analyse performance trade-offs across latency, quality, and cost
• Experiment with and apply state-of-the-art techniques in search, retrieval, and LLM-integrated systems
• Contribute to product and architectural decisions in a fast-moving environment

Must-haves:

• 5+ years of experience in software engineering or applied machine learning
• Strong programming skills in Python, Go, or C++
• Proven experience deploying ML models in production systems
• Hands-on experience with retrieval, ranking, recommendation, or similar ML problems
• Strong understanding of machine learning and modern deep learning techniques
• Experience working with large-scale data systems and high-throughput environments
• Ability to design evaluation frameworks and define meaningful model metrics
• Product-oriented mindset with a focus on impact and iteration
• Strong problem-solving skills and ability to work in a distributed team

Nice-to-haves:

• Experience with search systems or large-scale information retrieval
• Familiarity with embeddings, transformers, and modern NLP systems
• Experience working on LLM-powered or agent-based systems
• Contributions to open-source projects, technical publications, or conference talks
• Participation in competitive ML (e.g. Kaggle) or similar signals of strong technical ability

We conduct coding interviews as part of the process.

The role 

We are looking for a Senior Product Manager to join our Agentic Search team, building the search and retrieval infrastructure that powers AI agents and LLM-based applications at scale.

This is a hands-on IC role with real ownership. You will take full end-to-end responsibility over a core product area, from defining strategy through shipping and iterating based on real usage data. You will work within a small PM team reporting to the Director of Product, alongside engineering, design, and go-to-market, shaping how AI agents discover, retrieve, and act on web information in real time.

The product serves both a developer-facing PLG motion and a growing enterprise customer base, so you will need to be equally comfortable digging into API design and search quality as you are running customer discovery calls and informing competitive positioning. We are looking for someone who can operate as a senior strategic partner, not just an executor, and who has the potential to grow into a principal-level PM over time.

You’re welcome to work hybrid from Tel Aviv, Israel.

Your responsibilities will include: 

• Own a core product area end-to-end: strategy, roadmap, execution, and iteration based on real usage signals and customer feedback.
• Drive search quality and relevance improvements by working closely with engineering and research to define evaluation frameworks, benchmarks, and release criteria.
• Engage directly with enterprise customers and developer users to validate ideas, understand pain points, and shape product-market fit across both PLG and enterprise motions.
• Monitor the competitive landscape in agentic search and AI-powered retrieval, identifying shifts, threats, and opportunities that should inform product decisions.
• Collaborate with go-to-market teams (sales, solutions, growth) to ensure product positioning, ICP definitions, and enablement materials reflect product reality.
• Contribute to product strategy as a senior voice on a small, high-impact team, challenging assumptions and bringing independent judgment to key decisions.
• Lead product experiments and rapid iteration cycles, moving from hypothesis to prototype to production with clear success criteria.

We expect you to have: 

• 5+ years of product management experience, with a meaningful portion in developer tools, API platforms, or search and retrieval infrastructure.
• Track record of shipping products in fast-moving markets, working closely with engineering and design from concept through launch and iteration.
• Strong understanding of LLMs, AI agents, and how search and retrieval systems fit into agentic workflows. Hands-on technical background is a strong plus.
• Degree in computer science, engineering, or a related field, with the ability to engage deeply with technical architecture and tradeoffs.
• Comfortable operating in ambiguity: you can context-switch between strategic thinking and tactical execution without losing the thread.
• Proven ability to influence cross-functional stakeholders and drive alignment without formal authority.
• Excellent written and verbal communication: you can explain technical concepts clearly to both engineers and business stakeholders.

It will be an added bonus if you have: 

• Experience in search, information retrieval, NLP, or adjacent domains.
• Background in API-first or developer-platform businesses with both PLG and enterprise motions.
• Leadership experience in a high-growth technology company, especially post-acquisition or startup-within-a-larger-org environments.
• People management or mentoring experience (building the skills of other PMs).

The Product

In a rapidly evolving world, trust in AI depends on AI agents being grounded in fresh, verified real-world data. Search is the foundation that makes this possible.

We are building an agent-native search platform designed specifically for AI systems rather than human users. Our product provides programmatic, low-latency, and observable search APIs that AI agents use to retrieve, filter, and reason over real-world information at scale.

The Role

We are looking for a Senior Software Engineer to work on the runtime systems of a novel search engine tailored for agentic AI consumption.

In this role, you will focus on building low-latency, high-throughput systems that serve search queries in real time. You will work on the critical path of user-facing requests, where performance, predictability, and efficiency directly impact product quality. You will design and operate systems that handle thousands of requests per second under strict latency budgets, optimising every layer from request handling to data access and response assembly.

In this position, your responsibility will be to

• Design, implement, and operate core runtime services for serving search queries at scale
• Build and optimise request flows, including query processing, retrieval orchestration, and response assembly under strict latency budgets
• Develop systems that maintain performance and predictability under high load
• Optimise CPU, memory, and data access patterns in performance-critical paths
• Ensure reliability, observability, and predictability across production services
• Build well-tested systems with clear responsibilities and interaction contracts, while remaining flexible as architecture evolves
• Define and implement observability primitives, including structured logs, metrics, traces, and latency breakdowns
• Monitor throughput, latency, and resource usage, and drive improvements in performance and cost efficiency
• Collaborate with indexing and ML teams to integrate retrieval and ranking components, keeping ML logic decoupled from core system internals
• Support experimentation and iteration through controlled rollouts and rigorous benchmarking

You may be a good fit if you:

• Have 5+ years of experience as a software engineer working on production backend systems
• Have strong hands-on expertise in C++ or Rust in real-world, high-load services
• Have built and operated high-load, low-latency user-facing systems handling thousands of RPS under strict latency constraints
• Understand performance at a systems level — CPU, memory, networking, and data access
• Have operated your own code in production: deployed it, debugged incidents, and rolled back changes when necessary
• Think end-to-end about request flows rather than staying within isolated components
• Can balance correctness, latency, and development velocity, making pragmatic tradeoffs when scope or time requires
• Collaborate effectively across engineering, ML, and product teams, communicating clearly in cross-functional settings

Strong candidates may also have experience with:

• DBMS internals (open source or SaaS) and cloud infrastructure
• High-load web applications or large-scale APIs
• Performance-critical systems such as trading platforms or real-time data pipelines
• Low-level performance tuning and hardware-level optimisation
• Open-source contributions or active involvement in the engineering community
• Competitive programming or CTF participation
• SHAD or similar advanced technical programmes
• Conference talks or technical publications

We conduct coding interviews as part of the process.

The Role

Tavily team is building the search engine for AI agents. We believe the future of work will be led by AI agents, and that requires restructuring how the web is accessed. Our Search API provides web access for AI agents, enabling real-time internet search optimized for LLMs and Retrieval-Augmented Generation (RAG). We are backed by leading investors and serve developers and enterprises worldwide. Our team is fast-moving and ambitious. We ship quickly, iterate constantly, and care deeply about impact.

As a Software Engineer - Scraping Specialist, you’ll build the systems that power how AI interacts with the live web. You’ll design and implement large-scale, intelligent web acquisition pipelines, making sense of an ever-changing online ecosystem and transforming it into structured, high-quality data.

This role blends technical understanding of browsers, networks, and automation with hands-on engineering. You’ll work on adaptive systems that navigate modern websites, understand evolving web interaction ,detection systems, and gather meaningful information safely, efficiently, and at scale.

Your work will directly shape Tavily’s ability to provide AI agents with accurate, real-time knowledge of the world , bridging the gap between the open web and intelligent reasoning.

What You’ll Do

• Build distributed data acquisition systems that capture and structure the live web
• Investigate and analyze browser internals, fingerprinting, and anti-automation systems to develop stealthy, adaptive orchestration layers
• Prototype and deploy intelligent automation frameworks using Playwright, Puppeteer, and low-level browser control protocols (CDP)
• Conduct hands-on research into network flows, JavaScript-based protections, and emerging web standards affecting automation
• Collaborate with AI and infrastructure teams to integrate real-time web data into retrieval pipelines and LLM-powered agents
• Translate deep technical insights into production-grade components, balancing research freedom with engineering rigor
• Continuously evolve Tavily’s capabilities in resilience, speed, and authenticity of web interaction

What We’re Looking For

• 3–5 years of experience as a backend or systems engineer, ideally working with large-scale, distributed, or web-facing infrastructure
• Strong programming skills in Python or Node.js, with experience in Go or C++ considered a strong plus
• Proven experience building and maintaining browser automation systems (Playwright, Puppeteer, or CDP) in production environments
• Solid understanding of browser internals, network protocols, and web interaction mechanisms
• Experience designing high-performance, resilient systems that handle scale, concurrency, and complex orchestration
• Strong debugging and analytical skills - able to investigate edge cases, performance bottlenecks, and behavior under dynamic web conditions
• Comfortable working in a fast-moving environment, collaborating closely with product, AI, and infrastructure teams to ship reliable systems quickly
• Excellent documentation and communication skills to ensure smooth integration and operational visibility

Nice to Have

• Familiarity with cloud infrastructure, containerization (Docker), Kubernetes, and CI/CD
• Experience integrating AI or retrieval systems into production pipelines

The Product

In a rapidly evolving world, trust in AI depends on AI agents being grounded in fresh, verified real-world data. Search is the foundation that makes this possible.

We are building an agent-native search platform designed specifically for AI systems rather than human users. Our product provides programmatic, low-latency, and observable search APIs that AI agents use to retrieve, filter, and reason over real-world information at scale.

The Role

We are looking for a Senior Software Engineer to work on the indexing and data processing layer of a novel search engine tailored for agentic AI consumption.

In this role, you will focus on building systems that ingest, process, and organise massive volumes of data into efficient, queryable structures. You will work primarily on offline and nearline pipelines, ensuring that data is fresh, complete, and efficiently accessible by downstream retrieval systems. You will operate in an environment where throughput, scalability, and correctness are critical — designing systems capable of handling tens of gigabytes per second across continuously evolving datasets.

In this position, your responsibility will be to

• Design, implement, and operate large-scale indexing systems and data pipelines that sit at the core of our search infrastructure
• Build ingestion workflows for internal and external data sources, including web-scale crawling and structured feeds
• Develop and optimise indexing strategies balancing performance, freshness, and resource efficiency
• Work on storage formats, compaction strategies, and update mechanisms to keep data accessible and current
• Ensure reliability and predictability of pipelines under high-throughput conditions
• Build well-tested components with clear responsibilities and interaction contracts, while remaining flexible as the system evolves
• Define and implement observability primitives, including structured logs, metrics, and data quality signals across offline and nearline pipelines
• Monitor throughput, resource usage, and cost, and drive optimisations when business needs require it
• Collaborate with runtime and ML teams to ensure indexing outputs meet retrieval and ranking requirements
• Enable safe experimentation on indexing strategies and data processing logic through controlled rollouts and clearly defined quality signals

You may be a good fit if you:

• Have 5+ years of experience building production backend or data systems
• Have strong hands-on experience with Go in real-world, high-load services (experience with other systems languages such as C++ or Rust is a plus)
• Have worked on systems at significant scale — such as 10k+ RPS or 10+ GiB/sec throughput
• Have experience building or operating databases, data planes, or large-scale data pipelines
• Understand distributed systems fundamentals, including fault tolerance, failure modes, and horizontal scalability
• Have operated your own systems in production: handled incidents, made real-world tradeoffs, and understand what running data infrastructure at scale truly involves
• Think in terms of systems and data flows rather than isolated components, reasoning end-to-end about how data moves through the stack
• Can make pragmatic decisions under pressure without compromising long-term system health
• Collaborate effectively across infrastructure, ML, and product teams, communicating clearly in cross-functional settings

Strong candidates may also have experience with:

• Distributed data processing frameworks such as Spark, Flink, MapReduce, or Beam
• Content systems including web crawling, scraping, proxying, or anti-bot infrastructure
• Ad tech, social networks, or other large-scale content platforms
• DBMS internals (open source or SaaS) and cloud infrastructure
• Open-source contributions or active involvement in the engineering community
• Competitive programming or CTF participation (ICPC, IOI, or similar)
• SHAD or similar advanced technical programmes
• Conference talks or technical publications

We conduct coding interviews as part of the process.