Startups · AI

Product Engineer - Agent

Firecrawl · San Francisco HQ; Toronto Hub · On-site

← All jobs
About Firecrawl

Firecrawl is the web data API to search, scrape, and interact with the web at scale. Turn any source into clean Markdown or structured data your agents can ship with. Backed by Y Combinator.

About the role

Build and ship developer-facing agent features from idea to production Own the reliability and quality of agent behavior against a live, unpredictable web that constantly changes and fights back

What they're looking for

  • You've built and shipped developer-facing product that people actually used
  • You care about developer experience like a designer cares about pixels: latency, output schema, docs, the whole feel of it
  • You're comfortable owning ambiguous problems and turning them into shipped features
  • You move fast and close the loop. You'd rather ship, measure, and iterate than perfect on paper
  • Someone who needs a fully-specced ticket to start
  • A strong backend engineer who's indifferent to how the product feels to use
More about this role

You'll build the products developers and AI agents reach for when they need to take action on the web, not just read it. This is hands-on product engineering at the core of where Firecrawl is going: shipping the agent features that let LLMs navigate, decide, and act across the open web, owning them from idea to production, and obsessing over the details that make an API a joy to build on. You'll ship real product from day one, not tickets in a backlog.

Equity Range: Competitive equity. Details shared during the process.

Job Type: Full-Time

Experience: 3+ years building and shipping developer-facing product

Work Authorization: Must be authorized to work in the United States or Canada. We're not able to sponsor US visas right now. For Canada, we'll consider sponsorship on a case-by-case basis through our Toronto Hub.

Firecrawl is the easiest way to turn the web into data AI agents can use. One API call converts any URL into clean, LLM-ready markdown or structured data. It's the boring-hard problem everyone building with LLMs eventually hits, solved.

In September 2026 we raised a $75M Series B led by Smash Capital, and we're spending it building the largest repository of knowledge in...

Read the full posting on Firecrawl's site ↗

Engineering Team

Build your edge while you search

Free tools for founders and investors, plus VC Unfiltered, our take on startups, venture and the people who build them.