Get more replies from employers
Send a job-specific resume in minutes.
Worky is seeking a full-stack engineer for an early-stage AI infrastructure company building the continuous improvement layer for production AI agents. You’ll work at the intersection of developer tooling, observability, and applied AI, with high ownership from day one.
You’ll ship end-to-end with a backend emphasis across APIs, data models, and product surfaces, collaborating with AI teams to translate failures into product decisions while delivering production-quality code in a fast-paced
This is a full-stack engineering role with a backend lean at an early-stage AI infrastructure company building the continuous improvement layer for production AI agents. You'll work directly at the intersection of developer tooling, observability, and applied AI — helping engineering teams understand, debug, and improve their agents in production. The work is hands-on and high-ownership from day one.
Build core product experiences including agent investigation interfaces, eval workflows, trajectory debugging, verification, and replay systems.
Own problems end-to-end — talk to customers, understand where their agents fail, define solutions, build them, and iterate until they work.
Ship across the full stack with a backend emphasis: APIs, data models, internal systems, and product surfaces.
Build and shape an AI-powered investigation agent that runs large-scale analyses across production traces.
Design and implement platform systems including workspaces, permissions, billing, usage tracking, SDKs, and terminal-first developer experiences.
Work directly with AI teams deploying production agents to understand their failures and translate them into product decisions.
0–5 years of full-stack development experience with a strong track record of shipping production software end-to-end.
Proficiency in TypeScript, React, Next.js, Python, Node.js, and PostgreSQL in production environments.
Backend-focused skill set including strong API design and data modeling — not pure infrastructure or distributed systems.
Ability to engage directly with customers, identify pain points, and own solutions through to delivery.
Experience building platform systems such as workspaces, permissions, billing, usage tracking, SDKs, or account management.
Consistently clean, production-quality code and comfort working in fast-paced, ambiguous startup environments.
Bonus: experience with AI agents, LLM-powered products, developer tooling, observability products, or agentic system evaluation and debugging.
Strong CS fundamentals, whether from a top academic program or demonstrated through career experience at well-regarded tech companies or Series B+ startups.
Salary: $150,000 – $275,000 annually
Visa sponsorship: Not available
On-site in San Francisco, California, United States. This is a full-time, in-office role.