Quick overview
Job description
About the Role
Join a team building infrastructure that helps organizations improve the reliability of AI agents in production. In this backend-leaning full-stack role, you will work closely with customers and turn real-world agent challenges into polished product capabilities.
What You'll Do
Build product experiences for agent investigations, evaluation workflows, trajectory debugging, verification, and replay.
Own problems end to end by understanding customer needs, defining solutions, shipping features, and iterating based on results.
Develop APIs, data models, internal systems, and user-facing product surfaces across the stack.
Build agent capabilities for conducting large-scale investigations across production traces.
Design platform systems such as workspaces, permissions, billing, usage, SDKs, and terminal-first developer tools.
Work directly with AI teams to understand agent failures and translate those insights 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 end-to-end products with React or Next.js on the frontend and TypeScript, Python, or Node.js on the backend.
Ability to build polished interfaces, design clean APIs, model data effectively, and debug production issues across the stack.
Hands-on experience with AI agents, LLM-powered products, or agentic systems, including relevant APIs, architectures, evaluation, or debugging tools.
Experience influencing product decisions through engineering and working directly with customers to shape shipped solutions.
Strong computer science fundamentals and a track record of writing clean, consistent code.
Experience with developer tooling or platform features such as SDKs, CLIs, permissions, billing, or account management is useful.
Compensation & Benefits
Base salary: $230,000 to $300,000 annually. Visa sponsorship is available. Equity details were not provided.
Location
On-site in San Francisco, California, United States.