Software Engineer - AI Tooling

Posted 5 days ago

Apply Now

Resume Score

Check how well your resume matches this job before you apply.

Sign in to check score

About the role

  • Software Engineer building agents, MCP, and evaluation tooling for Supabase’s Postgres development platform. Improving how developers and AI agents use databases and backend services.

Responsibilities

  • Build and improve AI tooling including the MCP server, agent skills, agents, and the dashboard Assistant
  • Make new Supabase products usable by agents through tools, skills, and evaluations
  • Prototype and evaluate tooling for emerging AI technologies and determine what should reach production
  • Build evaluations, instrumentation, feedback loops, quality KPIs, and regression gates
  • Analyze how customers and agents use shipped tools and improve tooling, interfaces, and documentation
  • Design how documentation and product knowledge are exposed to agents and measure effectiveness
  • Build patterns and tools such as MCP on Edge Functions, vector embeddings, and agents running on Edge Functions
  • Enable contributions to Supabase’s agentic capabilities through contribution paths, templates, documentation, and review practices
  • Centralize shared AI logic for reuse across teams
  • Ship battle-tested tools with strong tests, benchmarking, and stress testing
  • Collaborate with AI Tooling Infrastructure engineers on reliability, authentication, and hosting
  • Work across Docs, CLI, Frontend, SDK, and other teams to deliver a coherent developer experience
  • Stay close to the fast-moving AI ecosystem

Requirements

  • 5+ years of professional software engineering experience
  • Strong TypeScript skills and knowledge of the JavaScript ecosystem, including npm, ES modules, bundlers, and compatibility
  • Deep familiarity with the AI ecosystem, current tools, agent patterns, and practical trade-offs
  • Experience building developer tools, product interfaces, or platform primitives used by engineers
  • Experience designing or using evaluation frameworks for AI quality, reliability, and task success
  • Understanding of baselines, variance, and cost in AI evaluation
  • Strong judgment about effective AI workflows and avoiding fragile or gimmicky experiences
  • Experience writing tests and validating reliability in real-world conditions
  • Knowledge of Postgres and relational database practices
  • Clear written communication and ability to work across product, engineering, and documentation teams
  • Ability to thrive in asynchronous, globally distributed teams
  • Comfort navigating ambiguity and moving quickly
  • Nice to have: experience with vector databases and embeddings, ideally pgvector
  • Nice to have: shipped customer-facing AI features or agents
  • Nice to have: documentation or structured knowledge designed for developers or agents
  • Nice to have: Braintrust or similar evaluation and tracing platform experience, or CI quality gates
  • Nice to have: open-source contributions or maintained developer tooling
  • Nice to have: experience across several product surfaces or teams

Benefits

  • Fully remote work
  • WeWork membership or co-working allowance usable anywhere in the world
  • ESOP (equity ownership)
  • Tech allowance for laptop, monitor, headphones, or other work equipment
  • Health insurance: 100% covered for employees and 80% for dependents
  • Annual company off-sites
  • Flexible, asynchronous work
  • Annual education allowance for courses, books, conferences, or other learning

Job title

Job type

Full Time

Experience level

Mid levelSenior

Salary

Not specified

Degree requirement

No Education Requirement

Tech skills

JavaScriptPostgresTypeScript

Location requirements

RemoteWorldwide

Report this job

Found something wrong with the page? Please let us know by submitting a report below.