You won't spend three months on a fake intern project. Interns ship to production, and responsibility scales with output. Strong interns get a full-time offer.
The work sits on the same two problems as everything we do: figuring out how LLMs decide which content and brands to surface, and using AI to create genuinely useful technical content instead of slop.
What you'll do:
- Ship TypeScript features used by real customers.
- Improve how our agents gather context, draft content, and learn from human review.
- Turn editorial judgment into workflows and quality checks.
- Work directly with founders and customers.
Who we're looking for:
- You're already curious about this space: you've tested why ChatGPT cites one source over another, built agents, or worked on making model output less generic.
- No professional experience required — TypeScript knowledge and proof of curiosity are.
- Bonus: prior work on context management.
In your first 30 days, you'll help build an extremely durable and powerful context system — infrastructure that lets agents pull context from noisy, changing sources (Slack, Linear, GitHub, docs) and produce strong first drafts. You'd build, evaluate, and improve a production system.
In-person in San Francisco for up to three months; remote may be possible for the first month. Meals at the office. Unlimited GPT and Claude, including Fable.