Software Engineer AI Tooling
Supabase
About this role
## About Supabase Supabase is the Postgres development platform, built by developers for developers. We provide a complete backend solution including **Database, Auth, Storage, Edge Functions, Realtime, and Vector Search**—deeply integrated and designed for growth. ## About the Role We’re looking for a **Software Engineer** to join our **AI Tooling** team and help shape how developers and agents build with Supabase. You’ll build and own our AI tooling, including: - **Agents** - **MCP server** - **Agent skills** - **Dashboard assistant** You’ll take an **eval-first** approach: every tool ships with **evals and metrics**, so we can prove—using evidence—that it makes agents better rather than worse. You’ll work closely with **Docs, CLI, Frontend, and SDK** teams, and with **AI Tooling Infrastructure** engineers who run these services in production. ## What You’ll Be Responsible For - Build and improve AI tooling we run today: **MCP server, agent skills, agents, and the Assistant** - Make new Supabase products usable by agents from day one (tools, skills, evals) - Build tooling for emerging AI technologies: **prototype quickly, evaluate honestly, decide with the team what ships to production** - Drive an **eval-first** approach with evals, instrumentation, feedback loops, and quality gates - Understand how customers and agents use what we ship, and turn that into improvements to tooling, interfaces, and documentation - Design how documentation and product knowledge are exposed to agents, and measure effectiveness - Build patterns/tools for customers to add AI to their apps (e.g., **MCP on Edge Functions, vector embeddings, agents on Edge Functions**) - Enable teams to improve Supabase’s agentic capabilities via contribution paths, templates, documentation, and review practices - Centralize shared AI logic so teams reuse it rather than duplicating it - Ship battle-tested tools with strong tests, benchmarking, and stress testing - Partner with AI Tooling Infrastructure on reliability, auth, and hosting - Work across Docs/CLI/Frontend/SDK to deliver a coherent developer experience ## You Might Be a Good Fit If You **Must have:** - **5+ years** of professional software engineering experience - Strong **TypeScript** and solid knowledge of the JavaScript ecosystem (npm, ES modules, bundlers, compatibility) - Deep familiarity with the AI ecosystem (agent patterns, practical trade-offs) - Ability to distinguish durable patterns from hype - Experience building developer tools / product interfaces / platform primitives used by other engineers - Experience designing/using evaluation frameworks to measure AI quality, reliability, and task success (baselines, variance, cost) - Strong judgment on where AI improves workflows and how to avoid fragile/gimmicky experiences - Ability to write tests and validate reliability in real-world conditions - Knowledge of **Postgres** and relational database practice - Clear written communication and ability to work across product, engineering, and docs in async, globally distributed teams - Comfort navigating ambiguity and moving quickly **Nice to have:** - Experience with **vector databases and embeddings** (ideally **pgvector**) - Examples of customer-facing AI features/agents you’ve shipped - Examples of documentation/structured knowledge for developers or agents - Experience with **Braintrust** (or similar eval/tracing platforms) or CI quality gates - Open-source contributions or developer tooling you’ve ma
Listing freshness
CronJobs last confirmed this listing 1h ago. If its source stops confirming the opening for seven days, this page is removed from active inventory.