T

Tavily

Search API for LLMs and RAG

Senior Software Engineer - Agentic Search, Web Access Engineer

Backend EngineeringConfirmed live in the last 24 hours
Full-timeNo salary listedIn-person

About the Job

Requirements

  • Have at least 5 years of experience building production systems.
  • Have expert-level knowledge in several of the listed areas: request lifecycle, client-side analysis, or running web-access systems in production.
  • Know HTTP/1.1, HTTP/2 and HTTP/3, TLS handshakes and TLS fingerprints (JA3/JA4), and header behavior.
  • Understand what a server can observe and what a client controls at each step of a request.
  • Use a systematic debugging method involving replaying captured browser traffic, comparing with a real browser on the same network path, and changing one variable at a time.
  • Read and analyze complex or obfuscated JavaScript, and observe what scripts measure by hooking browser APIs.
  • Understand how browser, device and network characteristics are measured, including canvas, fonts, WebGL, and screen and window metrics, and how they remain consistent across layers.
  • Use browser instrumentation and the Chrome DevTools Protocol for investigation.
  • Have production experience and be able to provide figures for requests per day, sites or hosts, and success rate, including how it was measured.
  • Have strong programming ability in at least one of Go, Python, Rust, or C++.

Responsibilities

  • Diagnose failed or degraded requests at the network and IP, TLS and HTTP/2, headers and session-state, client-side-script, or browser-characteristic layer.
  • Analyze how websites verify and classify clients, including how client-side scripts and protocol-level behavior affect the content served to different clients.
  • Build clients and tooling that behave consistently and compatibly with standard browsers across these layers, using a real browser when a lightweight client is insufficient.
  • Monitor access quality as websites change, detect regressions, identify their causes, and measure success using real content rather than status codes.
  • Build tools for traffic capture and comparison against real browsers, per-site and per-method success tracking, and measuring the cost of each successful fetch at scale.
  • Choose a fetch method for each host, from a lightweight HTTP client to a full browser, balancing quality against cost.

Desired Qualifications

  • Experience working at a web data provider, browser or web-security company, or a company that collects data from complex sources.
  • Contributions to browser networking or fingerprinting-related open-source tooling, or public write-ups explaining how client verification works.
  • Experience building or maintaining a patched browser.
  • Experience with networks, proxies, and IP reputation.
  • Experience with internet-scale distributed systems, Kubernetes, and cloud infrastructure.

About the Company

Tavily

Search API for LLMs and RAG

Tavily provides a search API for large language models (LLMs) and Retrieval-Augmented Generation (RAG) to access up-to-date, verifiable information. Its API returns optimized, contextually relevant results from multiple online sources, helping AI agents research and answer questions while reducing hallucinations, and it scales via a usage-based pricing model with a free tier. It stands out by pairing a commercial API with an open-source project (GPT Researcher) to showcase capabilities and build adoption, while prioritizing real-time data over general web search. Its goal is to become a core tool for AI development by delivering reliable external knowledge and scalable, verifiable data access for developers building AI agents and applications.

Company size
51-200
Company stage
Acquired
Total funding
$45M
Headquarters
New York City, New York
Founded
2023

Recently Posted Jobs

Explore more opportunities at Tavily

See more jobs