AI Platform Engineer
Core
Build the execution layer for Supabase's internal AI systems, including an event-triggered queue, a headless model-agnostic runtime, durable state, human review gates, and an evaluation layer to ensure agent trustworthiness.
Role type
Staff AI Platform Engineer
Builds
Internal AI operating system, agent platform, evaluation layer, and agent portfolio (reporting, drafting, triage, QA agents)
Domain
AI/LLM Agents, Internal Platform Engineering, Governance
Deliverable
production ML models
Required skills
Production LLM agent systems, API design, MCP servers, Python, GCP, Infrastructure as Code, Cloud warehouse, System architecture, Evaluation design, Golden suite creation, Behavioral assertions, CI gating, Human-in-the-loop design, Risk tiering, Least-privilege access, Audit logging, Cost instrumentation, Observability
Preferred skills
Open-source agent frameworks, LLM observability, Cost attribution, Public writing on agent reliability
Technologies
Python, GCP, Cloud warehouse, MCP servers
Responsibilities
Ship the agent platform to production, Own the evaluation layer and CI gates, Build and register the agent portfolio, Enforce governance in code, Design human contact protocols, Own platform tooling, Compute operating measures, Instrument platform return
Seniority
Staff, hands-on IC
