Skip to content
Top Notch Spot

Software Engineer AI Tooling

Supabase United States Engineering Posted 18 Nov 2026
Full-time Remote
Experience
Senior level · 5+ years
Location
United States
Work arrangement
Remote
Employment type
Full-time
Category
Engineering
Industry
Information Technology
Experience
Senior level · 5+ years
Openings
1

About the role

Supabase is looking for a Software Engineer to join its AI Tooling team and help shape how developers and agents build with Supabase. You will build and own Supabase's AI tooling — including agents, the MCP server, agent skills and the dashboard assistant — and as the field moves, you will build the tooling for new technologies too. Everything ships eval-first: every tool comes with evals and metrics, so the team knows with evidence that it makes agents better rather than worse. You will work closely with the Docs, CLI, Frontend and SDK teams, and with the AI Tooling Infrastructure engineers who run these services in production. Other teams contribute to AI Tooling to improve Supabase's agentic capabilities, and you will help them do that while keeping the quality bar high. This role suits someone who thrives in async, fast-paced environments and is excited about building developer tools that scale to millions. Supabase is the Postgres development platform, built by developers for developers, offering a complete backend solution including Database, Auth, Storage, Edge Functions, Realtime and Vector Search. The team is born-remote and open-source-first, with around 400 people in more than 60 countries. Location: Fully remote — Supabase hires globally. There are no Supabase offices, but the company provides a WeWork membership or co-working allowance you can use anywhere in the world.

Responsibilities

- 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: tools, skills and evals for new product surfaces, and tooling for new AI technologies as they emerge — prototype quickly, evaluate honestly, and decide with the team what is worth taking to production - 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 - Understand how customers and agents actually use what is shipped, and turn that 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 running on Edge Functions - Enable other teams to improve Supabase's agentic capabilities through contributions to AI Tooling: clear contribution paths, templates, documentation and review practice - Centralize shared AI logic so teams reuse it rather than duplicate it - Ship battle-tested tools, with strong tests, benchmarking and stress testing where it counts - Work with AI Tooling Infrastructure engineers on reliability, auth and hosting, and across Docs, CLI, Frontend, SDK and other teams to deliver one coherent developer experience

Requirements

5+ years of professional software engineering experience. Strong TypeScript and deep knowledge of the JavaScript ecosystem: npm, ES modules, bundlers and compatibility. Deep familiarity with the AI ecosystem — current tools, agent patterns and practical trade-offs — and experience building developer tools, product interfaces or platform primitives used by other engineers. Experience designing or using evaluation frameworks to measure AI quality, reliability and task success, including baselines, variance and cost. Knowledge of Postgres and relational database practice. Clear written communication, able to work across product, engineering and docs and thrive in async, globally distributed teams. Comfortable navigating ambiguity and moving quickly.

Preferred qualifications

Experience with vector databases and embeddings, ideally pgvector. Examples of customer-facing AI features or agents you have shipped. Examples of documentation or structured knowledge designed for developers or agents. Experience with Braintrust or a similar eval and tracing platform, or setting up CI quality gates. Open-source contributions or developer tooling you have maintained. Experience across several product surfaces or teams.

Benefits

Fully remote: Supabase hires globally, with a WeWork membership or co-working allowance usable anywhere in the world. ESOP (equity ownership) for every team member. Tech allowance to set up your ideal work environment. Health insurance covered 100% for employees and 80% for dependents, wherever you are. Annual company off-sites in a new city each year. Flexible, asynchronous work. Annual education allowance for courses, books, conferences or anything that supports your growth.

Skills

TypeScript JavaScript Ai agents Postgres LLM Developer Tools MCP pgvector Evaluation Frameworks

How to apply

  1. Select Apply now.
  2. You are taken to Supabase’s own application page to send your application.

Applying is free. We never ask candidates for money. The exact steps can differ by job and employer.