AI Tooling Software Engineer

Quick Facts

• Role: AI Tooling Software Engineer

Description

Build and own AI tooling for agents and developers, including the MCP server, agent skills, agents, and a dashboard assistant. Use an eval-first approach with evals, instrumentation, and metrics to prove tools improve agent outcomes without regressions. Collaborate across Docs, CLI, Frontend, SDK, and AI infrastructure to deliver a coherent developer experience.

Responsibilities

• Build and improve AI tooling (MCP server, agent skills, agents, Assistant)
• Prototype tools for new product surfaces and emerging AI technologies, then evaluate and decide what moves to production
• Drive eval-first development: create/improve evals, instrumentation, feedback loops, and define quality KPIs and regression gates
• Use customer/agent usage signals to improve tooling, interfaces, and documentation
• Define how documentation and product knowledge are exposed to agents and measure effectiveness
• Build patterns and tools for customer AI integration (e.g., MCP on Edge Functions, vector embeddings, Edge Function–based agents)
• Enable other teams to improve agentic capabilities via contribution paths, templates, documentation, and review practices
• Centralize shared AI logic to avoid duplication
• Ship battle-tested tools with strong tests, benchmarking, and stress testing
• Partner with AI tooling infrastructure on reliability, auth, and hosting
• Work cross-team to deliver one coherent developer experience

Requirements

• 5+ years of professional software engineering experience
• Strong TypeScript and JavaScript ecosystem knowledge (npm, ES modules, bundlers, compatibility)
• Deep familiarity with the AI ecosystem (agent patterns and trade-offs; durable patterns vs hype)
• Experience building developer tools, product interfaces, or platform primitives used by other engineers
• Experience designing/using evaluation frameworks for AI quality, reliability, and task success (baselines, variance, cost)
• Strong judgment about when AI improves workflows and how to avoid fragile or gimmicky experiences
• Ability to write tests and validate reliability under real-world conditions
• Knowledge of Postgres and relational database practices
• Clear written communication and comfort with async, globally distributed collaboration
• Comfort operating in ambiguity and moving quickly

Benefits

• Fully Remote (global hiring)
• ESOP (equity ownership)
• Tech allowance for your work setup
• Health benefits (company covers 100% employee insurance; 80% dependents)
• Annual off-sites
• Flexible, async working style
• Professional development annual education allowance