Software Engineer - AI Tooling

Responsibilities

• Build and improve the AI tooling we run today, including the MCP server, agent skills, agents and the Assistant.
• Drive an eval-first approach: build and improve evals, instrumentation and feedback loops, measure tools against a no-tool baseline, and help define the quality KPIs and gates that stop regressions shipping.
• Design how documentation and product knowledge are exposed to agents, and measure whether it works.
• Build patterns and tools that help customers add AI to their own apps, such as MCP on Edge Functions, vector embeddings and agents running on Edge Functions.
• Communicate clearly in writing, work across product, engineering and docs, and thrive in async, globally distributed teams.

Languages

Nice to have

• Experience with vector databases and embeddings, ideally pgvector.
• Examples of documentation or structured knowledge designed for developers or agents.
• Make new Supabase products usable by agents from day one: tools, skills and evals for new product surfaces. Also build tooling for new AI technologies as they emerge: prototype quickly, evaluate honestly, and decide with the team what is worth taking to production.

Other open roles here

• Engineering Manager - RealtimeRemote · worldwide
• Cloud Platform EngineerRemote · worldwide
• Platform Engineer, Edge & NetworkingRemote · worldwide
• Engineering Manager - PipelinesRemote · worldwide
• Multigres EngineerRemote · worldwide