Product Engineer — Interact

You'll own Firecrawl's browser interaction layer — the product that turns Firecrawl from a data extraction tool into the eyes of every AI agent on the web. Interact lets developers scrape a page and then pull data by acting on it: clicking, filling forms, navigating, completing authenticated workflows, extracting data static scraping can't reach.

This is our #1 product hire. You own the product decisions, not just the code. You talk to customers, figure out what they actually need (not what they say they need), make prioritization calls with incomplete information, and ship the right thing fast. You also build it — but the product judgment comes first.

Salary: $180,000 to $290,000/year (Range shown is for U.S.-based employees in San Francisco, CA. Compensation outside the U.S. is adjusted fairly based on your country's cost of living.)

Equity: Up to 0.15%

Location: San Francisco or Remote (Americas, UTC-3 to UTC-10)

Experience: 3+ years shipping developer-facing products in browser automation, web scraping, or agent tooling

About Firecrawl

Firecrawl is the easiest way to extract data from the web. Developers use us to reliably convert URLs into LLM-ready markdown or structured data with a single API call. In just a year, we've hit 8 figures in ARR and 120k+ GitHub stars by building the fastest way for developers to get LLM-ready data.

We're a small, fast-moving, technical team building essential infrastructure superintelligence will use to gather data on the web. We ship fast and deep.

What This Role Actually Is

A product owner who can engineer, not an engineer who occasionally thinks about product.

You talk to customers constantly. You develop an intuition for what agent developers are actually trying to do, not just what they're asking for. You make product bets — what to build, what to skip, what to kill — with imperfect data and real tradeoffs.

You also understand agentic systems deeply enough to know how agents choose and use tools, what makes an interaction API reliable vs. fragile at scale, and how to test whether agents actually prefer what you've built.

Then you build it yourself. Design to deployment, one person.

Day to day, you:

• Own the Interact product end-to-end — scrape-then-interact workflows, prompt-based interaction, session chaining, persistent profiles, live view

• Talk to customers and read every GitHub issue, Discord thread, and support ticket that touches Interact — not because someone asked, but because that's where the signal is

• Separate what customers ask for from what they actually need, and prioritize accordingly

• Ship fast product experiments — hypothesis, build, measure, decide in days

• Make prompt-based interaction reliable and magical: "click login and fill the email field" should just work, on any page, every time

• Dogfood relentlessly — you use the API before you ship changes to it

You're a Fit If You

• Think product-first. You form opinions about what to build and why before anyone scopes a ticket. You can hold ambiguity and still make a call.

• Have deep empathy for developers. You've built things developers loved. You know the difference between "works" and "delights" at the API level.

• Understand the scraping and browser data space. This isn't abstract to you — you know what breaks, what's hard, and what matters.

• Get agentic systems. You've thought about (or built) tooling for AI agents. You understand how agents select tools, where interaction fails, and what reliable agent workflows require.

• Ship fast and learn faster. You write code, own features, and iterate. Ambiguity doesn't slow you down.

You're Not a Fit If You

• Need a PM to tell you what to build

• Build great infra but don't care how it feels to the developer on the other end

• Haven't thought about how AI agents actually use browser interaction tools

• Optimize for technical elegance over shipping the right product

Benefits & Perks

Available to all employees

• Salary that makes sense — $180,000–$290,000/year, based on impact, not tenure

• Own a piece — Up to 0.15% equity in what you're helping build

• Generous PTO — 15 days mandatory, anything after 24 days, just ask (holidays excluded); take the time you need to recharge

• Parental leave — 12 weeks fully paid, for moms and dads

• Wellness stipend — $100/month for the gym, therapy, massages, or whatever keeps you human

• Learning & Development — Expense up to $1,000/year toward anything that helps you grow professionally

• Team offsites — A change of scenery, minus the trust falls

• Sabbatical — 3 paid months off after 4 years, do something fun and new

Available to US-based full-time employees

• Full coverage, no red tape — Medical, dental, and vision (100% for employees, 50% for spouse/kids) — no weird loopholes, just care that works

• Life & Disability insurance — Employer-paid short-term disability, long-term disability, and life insurance — coverage for life's curveballs

• Supplemental options — Optional accident, critical illness, hospital indemnity, and voluntary life insurance for extra peace of mind

• Doctegrity telehealth — Talk to a doctor from your couch

• 401(k) plan — Retirement might be a ways off, but future-you will thank you

• Pre-tax benefits — Access to FSAs and commuter benefits (US-only) to help your wallet out a bit

• Pet insurance — Because fur babies are family too

Available to SF-based employees

• SF HQ perks — Snacks, drinks, team lunches, intense ping pong, and peak startup energy

• E-Bike transportation — A loaner electric bike to get you around the city, on us

Interview Process

1. Application — Show us what you've shipped. A product, a GitHub link, a write-up.

2. Intro Chat (20 min) — Get to know each other.

3. Product Deep Dive (60 min) — How you think about product decisions, DX tradeoffs, and translating customer signal into shipped features.

4. Technical Deep Dive (60 min) — Architecture, system design, and how you think through hard problems live.

5. Paid Work Trial (1–2 weeks) — A real product problem. We evaluate shipping speed, product judgment, and DX quality.

6. Decision — Fast.

If you want to own the product that makes AI agents actually useful on the web — and you're the kind of person who talks to customers before writing code — this is your role.