Principal AI engineer leading production AI systems for CINC’s community - management platform. Building Cephai - powered automation, retrieval, and operational tools while mentoring engineering teams.
About the role
- Software Engineer building and operating AI backend infrastructure, including Supabase’s MCP server. Improving reliability, authorization, observability, and scalability for developer tools.
Responsibilities
- Build and operate production backend services behind Supabase’s AI products, including the MCP server
- Handle deployment, scaling, configuration, and release
- Structure, split, or reshape services to improve safety and maintainability
- Define, measure, and meet reliability targets; set SLOs, track error budgets, and prioritize fixes
- Participate in the AI Tooling team on-call rotation and respond to incidents
- Investigate and fix incidents, coordinate with other teams, and write follow-ups and runbooks
- Work the team support queue and turn recurring issues into fixes
- Own authentication and authorization for AI and agent clients, including OAuth apps, scoped tokens, permissions, and deprecation strategies
- Own observability through metrics, traces, logs, dashboards, and alerts
- Manage capacity and abuse for agent traffic, including rate limits, cost controls, safety controls, and degraded-dependency behavior
- Improve service architecture as systems grow
- Collaborate with Platform on shared code, ownership, and release processes
- Collaborate with SRE on infrastructure, alerting, and incident practices
- Contribute to AI Tooling team code where it affects reliability and security
Requirements
- 5+ years of experience building and running backend services in production, including carrying on-call
- Strong TypeScript or Go skills, with comfort working in the other
- Experience designing and operating APIs with real consumers, including versioning, error handling, rate limiting, and backward-compatible change
- Strong knowledge of OAuth, OIDC, JWT, and API authorization
- Good understanding of PostgreSQL and relational databases
- Familiarity with CI/CD, Docker, containerized deployments, and infrastructure as code
- Ability to debug across services using metrics, traces, and logs
- Clear written communication and ability to work with diverse stakeholders in async, globally distributed teams
- Comfort navigating ambiguity and moving quickly
- Deep expertise in at least one of: APIs and authentication; production operations; gateways and distributed systems
- Experience with agent tooling or AI agent and LLM client traffic is nice to have
- Experience extracting a service from a larger codebase while keeping existing clients working is nice to have
- Experience with Grafana, OpenTelemetry, Logflare, or similar observability tools and real SLO work is nice to have
- Open-source contributions, especially to Node.js, Go, TypeScript, or API tooling, are nice to have
Benefits
- Fully remote work
- WeWork membership or co-working allowance usable anywhere in the world
- ESOP (equity ownership) for every team member
- Tech allowance for laptop, monitor, headphones, or other work equipment
- Health insurance: Supabase covers 100% for employees and 80% for dependents, wherever you are
- Annual company off-sites
- Flexible, asynchronous work
- Annual education allowance for courses, books, conferences, or other learning
Job title
Job type
Experience level
Salary
Not specified
Degree requirement
No Education Requirement
Tech skills
Location requirements
Report this job
Found something wrong with the page? Please let us know by submitting a report below.
Freelance Mechanical CAD and Simulation Engineer training AI agents in real CAD environments. Designing geometry, building reference solutions, and evaluating engineering outputs.
AI Engineer building LLM - powered agentic workflows, evaluation systems, and MCP infrastructure for Superhuman Mail. Supporting Superhuman’s AI productivity platform across backend systems and applied AI.
Senior AI Architect designing PointClickCare’s shared AI platform for healthcare software teams. Establishing agentic architecture, governance, observability, and reusable engineering patterns.
Expert AI Engineer building spawning, behavioral AI, and systemic gameplay systems for CD PROJEKT RED’s Cyberpunk 2 RPG. Creating tools and mentoring developers across the open - world team.
Senior AI Engineer developing scalable navigation, pathfinding, and avoidance systems for CD PROJEKT RED’s Cyberpunk 2 RPG. Building designer tools and optimized open - world AI technology.
Senior AI Engineer building scalable navigation, pathfinding, and avoidance systems for CD PROJEKT RED’s Cyberpunk 2. Developing tools and optimized C++ gameplay systems for believable open - world AI.
Senior Software Engineer building privacy - preserving infrastructure for OpenMined’s federated AI nonprofit. Developing secure enclaves, PySyft, and reliable deployments for frontier AI evaluation.
Software Engineer building and deploying LLM - powered agents for Coalition, an active cyber - insurance and cybersecurity provider. Automating internal business workflows through MCP, evals, and production AI systems.
AI Engineer Intern researching AI security and cybersecurity technologies at American Express. Building prototypes, testing AI solutions, and evaluating secure enterprise applications.