About the Role

We're looking for a hands-on Applied AI Engineer who lives and breathes LLMs. This isn’t a research role — you’ll be solving real-world problems, shipping features, and building production-ready systems that make our agent smarter every week.

What You’ll Do

• Build LLM-powered systems: prompt chains, retrieval pipelines, eval frameworks
• Work across the stack from prototypes to production
• Own components like test generation, code summarization, context pruning, etc.
• Keep up with the latest in AI research, RAG, fine-tuning, and evals — and use them
• Work closely with founders and engineers to shape the direction of our product

You’ll Thrive Here If

• You’ve shipped LLM-based features or side projects before
• You’ve worked with RAG, fine-tuning, or synthetic data generation
• You’re comfortable reading papers and implementing them fast
• You care about clean engineering, not just demos
• You want to build a 0-to-1 product that people actually use

Tech Stack

Python, Typescript, LangChain, OpenAI, Claude, Pinecone/Chroma, Postgres, AWS

Perks

• Competitive salary and generous equity
• High ownership, no bureaucracy
• Work with founders and core team closely
• Fast shipping, real customers, and a big vision