Software Engineer - AI Tooling

• Join Supabase as a Software Engineer on the AI Tooling team, working fully remotely from anywhere in the world. • Build and own the AI tooling that shapes how developers and agents build with Supabase, including agents, the MCP server, agent skills and the dashboard assistant. • Take an eval-first approach, so every tool ships with evals and metrics that prove it makes agents better rather than worse. • Work closely with the Docs, CLI, Frontend and SDK teams, and with the AI Tooling Infrastructure engineers who run these services in production. • Help other teams contribute to AI Tooling and improve Supabase's agentic capabilities while keeping the quality bar high. • Thrive in an async, fast-paced environment while building developer tools that scale to millions.

• Bring 5+ years of professional software engineering experience. • Write strong TypeScript and know the JavaScript ecosystem well, including npm, ES modules, bundlers and compatibility. • Show deep familiarity with the AI ecosystem, including current tools, agent patterns and practical trade-offs. • Show experience building developer tools, product interfaces or platform primitives used by other engineers. • Use evaluation frameworks to measure AI quality, reliability and task success, and understand baselines, variance and cost. • Apply strong judgement about where AI improves workflows and how to avoid fragile or gimmicky experiences. • Know Postgres and relational database practice. • Communicate clearly in writing and work well in async, globally distributed teams.

• Use vector databases and embeddings, ideally pgvector. • Show examples of customer-facing AI features or agents you have shipped. • Know Braintrust or a similar eval and tracing platform, or how to set up CI quality gates. • Share open-source contributions or developer tooling you have maintained. • Bring experience across several product surfaces or teams.

• Build and improve the AI tooling Supabase runs today, including the MCP server, agent skills, agents and the Assistant. • Make new Supabase products usable by agents from day one with tools, skills and evals, and prototype tooling for emerging AI technologies. • Drive an eval-first approach by building evals, instrumentation and feedback loops, and defining the quality KPIs and gates that stop regressions shipping. • Turn insight into how customers and agents use Supabase into improvements to tooling, interfaces and documentation. • 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. • Enable other teams to contribute to AI Tooling through clear contribution paths, templates, documentation and review practice. • Work with the AI Tooling Infrastructure engineers on reliability, auth and hosting, and ship battle-tested tools with strong tests and benchmarking.

• Work fully remotely from anywhere, with a WeWork membership or co-working allowance to use anywhere in the world. • Receive ESOP, so every team member shares in the company's upside. • Use a tech allowance to set up your ideal work environment. • Enjoy 100% health insurance cover for employees and 80% for dependents. • Work asynchronously with flexibility to manage your own time. • Spend an annual education allowance on courses, books, conferences or other learning. • Join the whole company for an annual off-site in a new city each year.

Supabase is the Postgres development platform, offering a complete backend solution including Database, Auth, Storage, Edge Functions, Realtime and Vector Search. It is a born-remote, open-source-first company of around 400 people across 60+ countries, with over 540,000 community members. Supabase has raised over $1B, including a $500M Series F.