Product Engineer - Agent
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.
About the job
Responsibilities
- Build and ship developer-facing agent features from idea through production.
- Own the reliability and quality of agent behavior across a live, unpredictable web.
- Turn challenging problems such as multi-step navigation, action reliability, failure recovery, and task adherence into clean, developer-friendly APIs.
- Collaborate directly with the engineering team on roadmap decisions and tradeoffs.
- Use the product, review GitHub issues, and incorporate real developer feedback into product decisions.
Requirements
- 3+ years building and shipping developer-facing products used by customers.
- Strong product-engineering mindset with attention to developer experience, including latency, output schemas, documentation, and usability.
- Ability to own ambiguous problems and turn them into shipped features.
- Fast, iterative approach focused on shipping, measuring, and improving.
Compensation & Benefits
- Annual salary: $235,000–$260,000.
- Competitive equity.
- 15 days of mandatory PTO, with additional time available upon request.
- 12 weeks of 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.
- For US-based full-time employees: medical, dental, and vision coverage; life and disability insurance; supplemental insurance options; telehealth; 401(k); FSAs; commuter benefits; and pet insurance.
- For San Francisco-based employees: office snacks, drinks, team lunches, and an e-bike transportation program.
Skills
APIs, LLMs, Agent Navigation, Multi-Step Workflows, Backend Engineering, Developer Experience, GitHub
Similar jobs
Fullstack Engineering jobs
Firecrawl
San Francisco, CA
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.
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 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.