3 days ago

AI Platform Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 7 hours agoStatus: Live

Job Summary

Build the execution and evaluation platform that powers Supabase’s internal AI agent systems. Own production delivery of an event-triggered, durable, human-gated agent runtime with atomic rollback and end-to-end logging. Create golden-suite evaluations and governance enforced in code, including risk-tiered autonomy and auditability. Develop and instrument agent tooling, measures, and agent portfolios so the platform’s value is measurable and adoption is driven by usefulness.

Location: Anywhere

Workplace: Remote

Employment Type: Full time

Job Function: DevOps, Cloud & Infrastructure

Seniority: Mid level

Key Responsibilities

•Ship the agent platform to production, including an event-triggered queue, model-agnostic runtime, durable state, human review gate, atomic rollback, and full run logging.
•Own the evaluation layer and gate, building golden suites with behavioral assertions, safety cases, and CI regression blocking.
•Build and register the agent portfolio (reporting, drafting, triage, question-answering) across team/executive layers plus a meta layer to improve the platform.
•Enforce governance in code via risk tiers, least-privilege tool credentials, tool permission gates, and a decision audit log with autonomy constrained by design.
•Design and implement platform contact patterns (interruption budget, message bundling) and own platform tooling, measures, and self-instrumentation for operational value tracking.

Pay and Benefits

Perks:Remote WorkEsopHealth InsuranceTech AllowanceLearning BudgetAnnual Off-sites

Key Requirements

•Have shipped production LLM agent systems relied on by others, with operational history and at least one incident you can discuss.
•Design evaluations (golden sets, behavioral assertions, judge rubrics, pass thresholds) and gate CI based on results—not spot checks.
•Have done deep API work where the systems actually live, including authoring MCP servers.
•Own infrastructure end to end in Python on GCP, using a cloud warehouse and infrastructure as code (provision, deploy, monitor, roll back).
•Have strong taste for how software contacts humans and understand notification/trust tradeoffs.

Skills:Governance mindsetRecursive thinkingInversion thinkingAsync collaborationInstrumentation focus

Tech Stack:PostgresPostgreSQLEdge FunctionsRealtimeVector SearchPythonGCPMCPAPIsCloud warehouseInfrastructure as codeCI

Company Brief

Supabase

Provides an open-source backend as a service built on PostgreSQL, offering real-time APIs, authentication, storage, and edge functions to help developers quickly build and scale applications.

Industry: Cloud Computing

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Funding: Series B

Headquarters: New York, United States

Founded: 2020

Website LinkedIn

Loading job details...

Preparing the role view and application actions.

Supabase

3 days ago

AI Platform Engineer

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI

Last checked: 7 hours agoStatus: Live

Job Summary

Location: Anywhere

Workplace: Remote

Employment Type: Full time

Job Function: DevOps, Cloud & Infrastructure

Seniority: Mid level

Key Responsibilities

•Ship the agent platform to production, including an event-triggered queue, model-agnostic runtime, durable state, human review gate, atomic rollback, and full run logging.
•Own the evaluation layer and gate, building golden suites with behavioral assertions, safety cases, and CI regression blocking.
•Build and register the agent portfolio (reporting, drafting, triage, question-answering) across team/executive layers plus a meta layer to improve the platform.
•Enforce governance in code via risk tiers, least-privilege tool credentials, tool permission gates, and a decision audit log with autonomy constrained by design.
•Design and implement platform contact patterns (interruption budget, message bundling) and own platform tooling, measures, and self-instrumentation for operational value tracking.

Pay and Benefits

Perks:Remote WorkEsopHealth InsuranceTech AllowanceLearning BudgetAnnual Off-sites

Key Requirements

•Have shipped production LLM agent systems relied on by others, with operational history and at least one incident you can discuss.
•Design evaluations (golden sets, behavioral assertions, judge rubrics, pass thresholds) and gate CI based on results—not spot checks.
•Have done deep API work where the systems actually live, including authoring MCP servers.
•Own infrastructure end to end in Python on GCP, using a cloud warehouse and infrastructure as code (provision, deploy, monitor, roll back).
•Have strong taste for how software contacts humans and understand notification/trust tradeoffs.

Skills:Governance mindsetRecursive thinkingInversion thinkingAsync collaborationInstrumentation focus

Tech Stack:PostgresPostgreSQLEdge FunctionsRealtimeVector SearchPythonGCPMCPAPIsCloud warehouseInfrastructure as codeCI

Company Brief

Supabase

Provides an open-source backend as a service built on PostgreSQL, offering real-time APIs, authentication, storage, and edge functions to help developers quickly build and scale applications.

Industry: Cloud Computing

Company Size: Large (251 to 1,000 employees)

Growth: Scaleup

Funding: Series B

Headquarters: New York, United States

Founded: 2020

Website LinkedIn