AI Platform Engineer
New
S
SupabaseAI software
Remote, Global; We hire globally. We believe you can do your best work from anywhere.Full-Time
Salary not disclosed
Apply NowOpens the employer's application page
Job Details
- Required Skills
- PythonGCP
Requirements
- Have shipped production LLM agent systems that other people depended on, with operational history, real users, and an incident you can discuss.
- Design evaluations using golden sets, behavioral assertions, judge rubrics, pass thresholds, and CI gates.
- Have deep API experience with systems used for work and have authored MCP servers.
- Own infrastructure end to end in Python on GCP, using a cloud warehouse and infrastructure as code.
- Be able to provision, deploy, monitor, and roll back systems, and close architecture decisions independently.
- Demonstrate experience using agentic tools on real work in files and repositories, including triggers, permissions, human approvals, logging, and failure handling.
- Treat human notifications as spending a limited amount of trust.
- Strong signals include public work on agent frameworks, MCP servers, evaluation harnesses, or agent reliability.
- Strong signals include LLM observability, cost instrumentation, and building reports from agent-run logs.
- Experience building an internal platform voluntarily adopted by non-engineers is a strong signal.
Responsibilities
- Ship an event-triggered agent platform with a model-agnostic runtime, durable state, human review, atomic rollback, and complete run logging.
- Build golden evaluation suites, behavioral assertions, judge rubrics, safety cases, and CI gates that block regressions.
- Build and register reporting, drafting, linting, triage, and question-answering agents, along with agents that monitor and improve the platform.
- Enforce risk tiers, least-privilege credentials, tool-permission gates, decision audit logging, and human approval requirements in code.
- Design contact rules that include interruption budgets, message bundling, and useful context before requests.
- Own the compiler, validator, inventory integrity, and distribution of context and capabilities into repositories and chat surfaces.
- Build a production-data pipeline that computes a maturity grade for each team.
- Instrument agent work and compute the platform’s monthly return.
View Full Description & ApplyYou'll be redirected to the employer's site
