AI
ABOUT THE ROLE
Join a team building software infrastructure that helps organizations improve the reliability of AI agents in production. This backend-leaning full-stack role combines product engineering with hands-on work on agent investigation, evaluation, and debugging workflows.
WHAT YOU'LL DO
- Build product experiences for agent investigations, evaluations, trajectory debugging, verification, and replay.
- Own problems end to end by speaking with customers, understanding agent failures, defining solutions, and iterating on shipped products.
- Develop APIs, data models, internal systems, and user-facing product features across the stack.
- Build systems that run large-scale investigations across production traces.
- Design platform capabilities such as workspaces, permissions, billing, usage, SDKs, and developer workflows.
- Work with teams building production AI agents and translate their needs into product decisions.
WHAT WE'RE LOOKING FOR
- Typically 5 to 8 years of full-stack product engineering experience, with a backend emphasis.
- Experience shipping polished products end to end, including React or Next.js interfaces, APIs, data modeling, and production debugging.
- Strong hands-on skills with TypeScript and React, plus Python or Node.js; familiarity with PostgreSQL is relevant.
- Demonstrated experience building AI agents, LLM-powered products, or agentic systems, and familiarity with agent architectures, evaluation, or debugging tools.
- Product-minded engineering experience, including customer discovery and influencing product decisi