AI Platform Engineer

• Build the execution layer for Supabase's internal AI systems as the sole engineer on a new central team standing up an AI-native internal operating system. • Ship the agent platform to production including an event-triggered queue, a headless model-agnostic runtime, durable state, a human review gate, atomic rollback, and full run logging. • Build the evaluation layer that makes agents trustworthy, and the agents themselves, across everything from executive reporting to a meta layer that watches the platform and improves it.

• Have shipped production LLM agent systems that other people depended on, with operational history, real users, and at least one incident you can talk through. • Design evaluations rather than spot checks, building golden sets, writing behavioural assertions, defining judge rubrics, setting pass thresholds, and gating CI on the result. • Have done deep API work against the systems work actually lives in, and have authored MCP servers, knowing the specific failure modes of those APIs. • Own infrastructure end to end in Python on GCP with a cloud warehouse and infrastructure as code, provisioning, deploying, monitoring, and rolling back your own systems. • Close architecture decisions yourself rather than routing them onward. • Have taste about how software contacts humans, treating every notification as spending a limited amount of trust.

• Have public work in this space such as an open-source agent framework, an MCP server, an evaluation harness, or writing on agent reliability that other practitioners cite. • Bring LLM observability and cost instrumentation experience including tracing agent runs, attributing spend per run, and building queries that turn raw logs into actionable reports. • Have built an internal platform that non-engineers adopted voluntarily and can describe what you changed after watching them use it.

• Ship the agent platform to production with 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 with golden suites using behavioural 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 covering reporting, drafting, linting, triage, and question-answering agents across executive, team-lead, and individual-contributor layers, plus a meta layer that observes the platform and improves it. • Enforce governance in code with risk tiers the pipeline actually enforces, least-privilege credentials per agent, tool-permission gates, a decision audit log, and autonomy classes where the dangerous class has no code path. • Design how the system contacts people with a hard interruption budget per person, message bundling instead of a stream of pings, and a structure that gives something useful before it asks for anything. • Own the platform tooling including the compiler and validator, inventory integrity, and the paths that distribute context and capabilities into repositories and chat surfaces. • Compute operating measures from production data through a pipeline from raw system activity to a computed maturity grade per team. • Instrument the platform's own return with a ledger that logs work each agent absorbs and computes the monthly figure.

• Work fully remotely from anywhere in the world. • Receive ESOP equity ownership in the company. • Get a tech allowance to set up your ideal work environment. • Receive 100% employer-covered health insurance with 80% coverage for dependents. • Attend annual company off-sites in a new city each year. • Work flexibly and asynchronously with full trust to manage your own time. • Receive a professional development allowance for courses, books, conferences, and learning. • Access a WeWork membership or co-working allowance usable anywhere in the world.

Supabase is the open-source Postgres development platform that 7M+ developers and thousands of enterprises depend on every day. Providing a complete backend solution including Database, Auth, Storage, Edge Functions, Realtime, and Vector Search, Supabase is born-remote and open-source-first with around 400 team members across 60+ countries. The company has raised over $1B including a $500M Series F.