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 USD/year (SF) / $217,000–$233,000 CAD/year (Toronto)
Equity Range: Competitive equity. Details shared during the process.
Location
San Francisco, CA (SF HQ) or Toronto, ON (Toronto Hub). Hybrid, onsite 3+ days a week.
Job Type: Full-Time
Experience: 5+ years
Work Authorization: Open to candidates already authorized to work in the US or Canada. In the US, we also support H-1B transfers, F-1 OPT and STEM OPT, TN (Canada and Mexico), and E-3 (Australia). We’re not able to sponsor new H-1B visas for candidates outside the US. For Canada, we’ll consider work permit sponsorship case by case through our Toronto Hub.
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
Own the problem end to end, from question to shipped answer
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