4 months ago
Remote, WorldwideSenior
Responsibilities
- Ship the production AI agent platform with an event-triggered queue, model-agnostic runtime, durable state, human review gates, atomic rollback, and complete run logging.
- Build and own the evaluation layer with golden suites, behavioral assertions, judge rubrics, safety cases, pass thresholds, and CI regression gates.
- Build and register reporting, drafting, linting, triage, question-answering, and platform-improvement agents.
- Enforce risk tiers, least-privilege credentials, tool-permission gates, decision audit logging, ownership registration, and human approval requirements in code.
- Design notification and contact systems with interruption budgets, message bundling, and useful context before requests.
- Own platform tooling including the compiler, validator, inventory integrity, and context and capability distribution paths.
- Compute team operating measures and maturity grades from production data, and instrument the platform’s operational value through a work-absorption ledger.
- Provision, deploy, monitor, and roll back the platform while closing architecture decisions independently.
Requirements
- Production experience shipping LLM agent systems with real users, operational history, and incidents that can be discussed.
- Experience designing evaluations with golden sets, behavioral assertions, judge rubrics, pass thresholds, and CI gating.
- Deep API experience with systems where work actually lives and experience authoring MCP servers.
- End-to-end infrastructure ownership using Python on GCP, including provisioning, deployment, monitoring, and rollback.
- Strong judgment about human-facing software, notifications, trust, and safe agent autonomy.
- Preferred qualifications include public work such as an open-source agent framework, MCP server, evaluation harness, or cited writing on agent reliability.
- Experience with LLM observability, agent-run tracing, per-run cost attribution, and queries that turn raw logs into actionable reports is a strong signal.
- Experience building an internal platform adopted voluntarily by non-engineers is a strong signal.
Benefits
- Fully remote, with global hiring and a WeWork membership or coworking allowance.
- ESOP equity ownership for every team member.
- Tech allowance for a laptop, monitor, headphones, or other work equipment.
- Supabase covers 100% of employee health insurance and 80% for dependents wherever employees are located.
- Annual company off-sites in a new city.
- Flexible asynchronous work.
- Annual professional-development and education allowance.
Tech Stack
Categories
About Supabase
Supabase builds an open-source Postgres-based backend platform for developers, bundling database, authentication, storage, realtime APIs, edge functions, and vector search. It monetizes through a managed cloud service and enterprise offerings while remaining deployable self-hosted. Founded in 2020 and privately held, the company operates globally with a fully remote team. Developers use Supabase as a Firebase alternative to launch quickly and scale production applications on PostgreSQL.