AI Platform Engineer

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. All services are deeply integrated and designed for growth.

About the Role

We are hiring an AI Platform Engineer to build the execution layer for Supabase's internal AI systems.

Supabase is building an AI-native internal operating system: a common way of working across the company where AI carries a meaningful share of the operational load rather than sitting alongside it as an assistant. We are standing up a new central team to build those systems, enable the teams, and embed AI operations throughout the organization. You are the engineer on that team.

The execution layer is yours. You will build the platform that actually runs agents: an event-triggered queue, a headless model-agnostic runtime, durable state so work survives a restart, a human review gate, atomic rollback, and full logging of every prompt, tool call and decision so any run can be reconstructed. You will build the evaluation layer that makes any of it trustworthy, because an agent that cannot be measured cannot be trusted with anything beyond reading. And you will build the agents themselves, across everything from executive reporting down to a layer of agents that watch the platform and improve it.

This is a governance-heavy environment by design, and that is the interesting part of the problem. Agents are risk-tiered from read-only internal data through to external-facing output, with review depth, evaluation requirements and human approval scaling by tier. Some capabilities are permanently off limits: an agent may read and report, it may carry a human-authored update into a system of record once a human consents, and it may initiate contact within a strict budget, but it may never autonomously write a commitment (an owner, a due date, a status) into a shared work system. Your job is to make that structurally impossible rather than merely forbidden.

You will be the only engineer on this platform. You will close open architecture decisions yourself, own the infrastructure end to end, and instrument the system so it reports its own return.

Responsibilities

• Ship the agent platform to production: Build an event-triggered queue, a headless model-agnostic runtime, durable state that survives a failed run, a human review gate, atomic rollback, and complete run logging in the warehouse.
• Own the evaluation layer: Switch on the gate that depends on it. Golden suites with behavioral assertions, judge criteria with a written rubric, safety cases that must pass on every run, and a CI gate that blocks regressions from merging.
• Build and register the agent portfolio: Reporting, drafting, linting, triage, and Q&A agents across executive, team-lead, and individual-contributor layers, plus a meta layer that observes and improves the platform.
• Enforce governance in code: Risk tiers enforced by the pipeline, least-privilege credentials per agent, tool-permission gates, a decision audit log, and autonomy classes where dangerous paths have no code path.
• Design human contact mechanisms: Enforce a hard interruption budget per person, message bundling over constant pings, and value-first interactions.
• Own platform tooling: The compiler, validator, inventory integrity, and distribution paths into repositories and chat surfaces.
• Compute operating measures: Build pipelines from raw activity to team maturity grades defensible via direct queries.
• Instrument platform return: Maintain a ledger measuring and logging work absorbed per agent to track financial and time return.

Qualifications

Must Have

• Shipped production LLM agent systems that other people depended on, with operational history, real users, and incidents to speak to.
• Experience designing evaluations with golden sets, behavioral assertions, judge rubrics, pass thresholds, and CI gating.
• Deep API integration experience against core work systems and authoring of Model Context Protocol (MCP) servers.
• End-to-end infrastructure ownership in Python on GCP, including a cloud data warehouse and Infrastructure as Code.
• Strong product taste and discretion regarding notification frequency and human interaction.

Strong Signal

• Public contributions in the agent space: open-source agent frameworks, MCP servers, evaluation harnesses, or widely cited writing on agent reliability.
• Experience with LLM observability, cost tracing, and usage attribution.
• Proven track record of building internal platforms that non-engineers adopted voluntarily.