🛠 Tech Stack

💼 About This Role

You'll build and ship LLM-powered product features end-to-end, including retrieval-augmented generation and tool-calling. You'll design evals, guardrails, and monitor production cost and quality. This role offers the chance to work on safety-critical aviation systems with a fast-moving team.

🎯 What You'll Do

• Design and implement RAG and tool-calling flows using LangChain or equivalent.
• Ship APIs and workers in Python or TypeScript with clear contracts.
• Develop chunking, embeddings, and indexing for documents and time series.
• Create offline evals and online metrics for quality and latency.

📋 Requirements

• Experience shipping LLM features in production.
• Strong Python or TypeScript coding skills.
• Deep understanding of RAG, embeddings, and vector search.
• Ability to define evals and success metrics for LLM systems.

✨ Nice to Have

• Experience with Bedrock, OpenSearch Serverless, or pgvector.
• Multimodal work with time series or video.
• Aviation or safety-critical domain experience.

🎁 Benefits & Perks

• 🏥 100% medical premium for employees
• 🌴 3 weeks PTO plus 13+ holidays
• 📱 Monthly phone and wellness stipends
• 💰 401(k) offered

📨 Hiring Process

Estimated timeline: 2-4 weeks · AI estimate

1. 1Recruiter Call· 30 min
2. 2Technical Interview· 60 min
3. 3Onsite Interview· 180 min