Agent Experience Engineer
Build and improve how AI agents discover, interpret, and use Firecrawl by shipping agent-facing product experiences and rigorous A/B tests. The role requires 5+ years of experience, strong product engineering ability, behavioral data fluency, and independent execution.
About the job
Responsibilities
- Design and ship A/B tests across agent-facing surfaces, including MCPs, CLIs, skills, APIs, and documentation.
- Analyze behavioral and experiment data, form hypotheses, and turn results into rapid product improvements.
- Track emerging agent tools, models, and harnesses, including Hermes and OpenClaw.
- Investigate how agents discover, interpret, select, and use tools and capabilities.
- Operate independently and own the problem end to end.
- Apply scientific rigor to product development while prioritizing shipping.
Requirements
- 5+ years of professional experience.
- Demonstrated ability to ship high-quality products quickly.
- Experience designing A/B tests, interpreting behavioral data, and acting on findings.
- Familiarity with agent-facing surfaces such as MCPs, CLIs, skills, APIs, and documentation.
- Active interest in emerging AI tools, models, and harnesses.
- Experience building for AI agents.
- Strong independence, agency, curiosity, and learning speed.
Nice-to-haves
- Background as an ex-founder, early-stage startup engineer, prolific open-source contributor, or creator of impressive public work.
Compensation & Benefits
- Salary: $235,000–$260,000 per year.
- Competitive equity.
- 15 days mandatory PTO, with additional time available up to 24 days by request.
- 12 weeks fully paid parental leave.
- $100/month wellness stipend.
- Up to $1,000/year for learning and development.
- Team offsites and a three-month paid sabbatical after four years.
- US-based employees: medical, dental, and vision coverage; life and disability insurance; optional supplemental insurance; telehealth; 401(k); FSAs; commuter benefits; and pet insurance.
- San Francisco employees: office snacks, drinks, team lunches, and a loaner e-bike.
Interview Process
- Application review.
- Introductory chat.
- Technical chat focused on shipped work and an agent-experience problem.
- Founder chat.
- Paid 1–2 week work trial.
Skills
A/B Testing, Behavioral Data Analysis, Mcp, Cli, APIs, AI Agents, Experiment Design, Documentation
Similar jobs
Fullstack Engineering jobs
Firecrawl
San Francisco, CA
Own and evolve Firecrawl’s open-source repositories, maintaining the core self-hosting experience and building new context primitives such as a document parsing engine. The role requires 5+ years of experience, a substantial open-source track record, and strong software engineering judgment.
Firecrawl
San Francisco, CA
Build and ship developer-facing products that enable AI agents to navigate and act across the web. The role requires 3+ years of experience delivering customer-used products, strong API and developer-experience instincts, and comfort owning ambiguous problems end to end.
Firecrawl
San Francisco, CA
Build and own developer-facing document-parsing features that transform complex files into reliable, LLM-ready markdown and structured JSON. The role requires at least three years of shipping products or APIs used by developers, strong product judgment, and comfort solving ambiguous parsing problems.
Runway
United States
Build full-stack AI-powered video creation and collaboration features, including rich interfaces, backend APIs, LLM experiences, and production systems. The role requires 5+ years of software engineering experience, strong JavaScript or TypeScript fluency, and experience integrating third-party AI APIs.
Anyscale
San Francisco, CA
Build developer-facing tooling, platform services, and ML infrastructure across Ray and Anyscale, spanning CLI, SDK, APIs, workspaces, observability, and production serving. Requires 5+ years of production software experience, strong systems fundamentals, and familiarity with machine learning tooling.