What you'll do
Design and ship AI Assist features: drafting automations, suggesting improvements, and explaining failed runs
Build prompts, tools, and evaluation suites that measure quality, not just demos
Add guardrails so AI output is reviewed before anything goes live
Work with product and design on how people review and approve suggestions
Monitor cost, latency, and quality in production
What we're looking for
3+ years of engineering experience, including shipping LLM-powered features
Strong skills with TypeScript or Python
Experience building evaluations and measuring model quality
Good judgment about when AI should and shouldn't act on its own
Nice to have
Experience with agents or tool-calling systems
Background in developer tools or automation
Experience with retrieval and structured outputs
What will you get
Competitive salary and meaningful equity
Fully remote with flexible hours, plus team meetups twice a year
A generous budget for AI tools, model usage, and research time
A yearly learning budget for books, courses, and conferences
A top-spec laptop, a home office stipend, and 25 days of paid time off
