About the Role
Join a product engineering team building software that helps organizations improve the reliability of AI agents in production. This backend-leaning, full-stack role combines customer problem-solving with hands-on development across agent investigation, evaluation, and debugging workflows.
What You'll Do
Build product experiences for agent investigations, evaluations, trajectory debugging, verification, and replay.
Work directly with customers to understand agent failures, shape product decisions, and iterate on solutions.
Develop APIs, data models, internal systems, and user-facing product surfaces across the stack.
Build systems that support large-scale investigations using production traces.
Design platform capabilities such as workspaces, permissions, billing, usage, SDKs, and terminal-first developer tools.
Collaborate with teams building production AI agents and turn their needs into shipped product improvements.
What We're Looking For
Five to eight years of full-stack product engineering experience, with a backend emphasis.
Experience shipping end-to-end products, including polished interfaces with React or Next.js and backend services.
Strong TypeScript skills and hands-on experience with Python or Node.js; familiarity with PostgreSQL is relevant.
Experience building AI agents, LLM-powered products, or agentic systems, with practical familiarity with LLM APIs, evaluation, or debugging tools.
Ability to design clean APIs and data models, debug production issues, and influence product direction through engineering work.
Strong computer science fundamentals and experience working directly with customers or product teams.
Compensation & Benefits
Base salary: $230,000 to $300,000 annually. Visa sponsorship is available.
Location
On-site in San Francisco, California, United States.