Agent Experience Engineer

Visa Hunt; San Francisco (CA); On-site; USD 235,000 - 260,000; Full time

Benefits offered by this job

Salary and equity package

Generous PTO

Parental leave

Wellness stipend

Learning & Development

Team offsites

Sabbatical

Job summary

Firecrawl is seeking an Engineer to own how agents discover, understand, and use our platform. You will design rigorous A/B tests across MCPs, CLIs, APIs and documentation, shipping improvements quickly based on experimental results.

The role blends engineering velocity with scientific rigor, focusing on product outcomes rather than pure research. Ideal candidates have 5+ years of experience, ship high-quality products fast, and stay current with emerging agent tools like Hermes and OpenClaw.

Qualifications

• 5+ years of experience in product-engineering roles.
• Strong ability to design and ship A/B tests for agent-facing surfaces.
• Experience turning experiment results into product improvements.
• Familiarity with tools/models used in agent tooling (Hermes, OpenClaw).
• Ability to form hypotheses about how agents discover and use tools, then test them in production.

Responsibilities

• Design and ship A/B tests across agent-facing surfaces — MCPs, CLIs, skills, APIs, documentation — to see how agents actually use Firecrawl
• Turn experiment results into shipped product improvements, fast
• Track emerging agent tools, models, and harnesses closely to understand implications
• Form hypotheses about agent tool usage and test them in production
• Operate independently in a space without a defined playbook
• Bring scientific rigor to product development without making it a research project

Skills

A/B testing

Experimentation

Product mindset

Data-driven decision making

Agent-facing surfaces

Shipping velocity

Tools

Hermes

OpenClaw

APIs

Job description

Agent Experience Engineer

Firecrawl is looking for a high-agency, product-minded engineer with strong experimental and data instincts to own how agents discover, understand, and use Firecrawl. You'll ship fast, run rigorous A/B tests, and turn what you learn into a better product — for an audience that isn't human.

This is not a pure research or data science role. We want an engineer who brings scientific rigor to product development: forming hypotheses, running experiments, analyzing results, and shipping better agent experiences. Prior agent experience is valuable, but raw engineering ability, shipping velocity, and learning speed matter most.

Salary Range: $235,000–$260,000/year

Equity Range: Competitive equity — details shared during the process.

Location: San Francisco, CA (on-site)

Job Type: Full-Time

Experience: 5+ years

Visa: Must be legally authorized to work in the United States. We're not able to sponsor visas right now, though that may change down the line.

About Firecrawl

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 - the boring-hard problem everyone building with LLMs eventually hits, solved.

We hit 8 figures in ARR in year one and more than doubled it in year two. We have 175k+ GitHub stars, and developers, agents, and category-defining AI companies build on us every day. Growth like this is rare, and we're just getting started.

We're a small team punching far above our weight. Everyone here owns a real piece of the product and company, end to end, and runs it themselves - no hiding behind process or headcount.

This is a place for people who want to work at the frontier: an AI company building the infrastructure other AI companies run on, not one bolting AI onto an existing product. We move fast, go deep, and are building the tools superintelligence will rely on to gather data from the web.

What You'll Do

• Design and ship A/B tests across agent-facing surfaces — MCPs, CLIs, skills, APIs, documentation — to see how agents actually use Firecrawl

• Turn experiment results into shipped product improvements, fast

• Track emerging agent tools, models, and harnesses (Hermes, OpenClaw, and whatever's next) closely enough to know what they mean for us

• Form hypotheses about how agents discover, interpret, and select tools and capabilities, then test them in production

• Operate independently in a space that doesn't have a playbook yet — own the problem end to end

• Bring scientific rigor to product development without turning it into a research project

What We're Looking For

• A track record of shipping high-quality products fast — not prototypes, not decks

• Comfort designing A/B tests, reading behavioral data, and acting on what it tells you

• Familiarity with agent-facing surfaces: MCPs, CLIs, skills, APIs, documentation

• You actively follow emerging AI tools, models, and harnesses — Hermes, OpenClaw, whatever's next

• Genuine curiosity about how agents select tools, interpret capabilities, and interact with products

• High agency — you can operate independently in a space that doesn't have a playbook yet

• Often an ex-founder, early startup engineer, prolific open-source contributor, or someone with impressive public work

What We're NOT Looking For

• Someone looking for a pure research or data science role — this is a shipping job first

• Someone who needs a mapped-out roadmap before they can move

• Someone who treats experimentation as a report to write rather than a lever to pull

• Someone excited by agents in theory who hasn't actually built for them

A Note On Pace

We operate at an absurd level of urgency because the window for what we're building won't stay open forever. If that excites you, keep reading. If it doesn't, no hard feelings — but this role probably isn't for you.

Benefits & Perks

Available to all employees

• Salary that makes sense — $235,000–$260,000/year, based on impact, not tenure

• Own a piece — Gain competitive 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 all parents

• 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

Intro Chat (~25 min) — A quick conversation to get to know each other before we go deep. We'll talk about what you've been working on, what drew you to Firecrawl, and what you're looking for in your next role. Time for your questions too.

Technical Chat (~45 min) — We'll walk through something you've built and a real agent-experience problem from our world. Come ready to think out loud; we care how you reason and experiment, not whether you know the "right" answer going in.

Founder Chat (~25 min) — Culture, pace, ownership, and how you like to work. Time for your questions too.

Paid Work Trial (1-2 weeks) — Ship something real with the team, paid at a contractor rate. It's the truest signal for both sides: you see what building at Firecrawl actually feels like, and we see how you operate.

Decision — We move fast after the trial.

If you want to define how agents experience the web, from the ground up, you should join us.