🛠 Tech Stack

💼 About This Role

You'll shape how AI shows up across ReadMe's product, working on systems that are already live across thousands of developer hubs. You'll help decide what gets built, why it matters, and how it works end-to-end. This role covers AI-driven documentation, conversational answers, and agent-ready APIs.

🎯 What You'll Do

• Design end-to-end AI systems combining LLMs, embeddings, and retrieval pipelines.
• Build grounding and retrieval layers for docs and OpenAPI specs.
• Define evaluation systems measuring accuracy, latency, cost, and user impact.
• Own production reliability including observability, fallbacks, and rate limiting.

📋 Requirements

• Experience building with LLMs in production.
• Strong JavaScript/TypeScript or Python experience.
• Experience with RAG embeddings and retrieval systems.
• Experience designing and shipping end-to-end systems from backend to UI.

✨ Nice to Have

• Familiarity with real-world edge cases like messy data and ambiguous queries.
• Experience improving AI reliability, observability, and production readiness.
• Strong instincts around when to use AI vs. deterministic approaches.

🎁 Benefits & Perks

• 🏖️ Remote work options available.
• 🏢 Hybrid options in San Francisco, New York, or Columbus.
• 🦉 Small team culture with big impact.
• 📖 Shape product direction without PM handing tickets.
• 🌱 Growth from day one with meaningful ownership.

📨 Hiring Process

30 min phone chat with VP Engineering, 30 min with Engineering Manager, technical assessment, then 3.5-5 hour onsite over Zoom.