About Tavily
Tavily 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.
The Role
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.
This position is based in Israel and requires existing legal authorization to work in Israel. Tavily is not able to provide visa sponsorship for this role.
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
Skills Required
- 3-5 years of experience as a backend or systems engineer
- Strong programming skills in Python or Node.js
- Experience in Go or C++ considered a strong plus
- Proven experience building and maintaining browser automation systems 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
- Excellent documentation and communication skills
What We Do
Search. Extract. Crawl. The web access stack built for builders, by builders. Tavily powers the next generation of agents with a suite of tools for real-time Search, structured data Extraction, and fully-rendered Crawling — everything agents need to access and reason over the live web. Purpose-built for RAG, autonomy, and production-grade agent systems.
