Intelligence
AI Engineer
Build LLM-powered products and agents — RAG pipelines, evals, and Claude-driven tools that ship to production.
What you'll do
- Build LLM features: retrieval, agents, and tool use
- Design evaluation harnesses that catch regressions
- Add guardrails for when a model is confidently wrong
- Take prototypes to production reliability
What we're looking for
- Hands-on experience with LLM APIs in production
- Understanding of RAG, embeddings, and vector search
- Strong Python or TypeScript
- Judgement about where AI does and does not belong
What we offer
100% remote, async-friendly
Top-of-market compensation
4-day focus weeks
Learning & conference budget
Latest hardware, your choice
Profit sharing
Role details
- Type
- Full-time
- Team
- Intelligence
- Location
- Remote
Ready to build something great?
Whether you have a fully-specced project or just a spark of an idea, we'd love to hear it. Book a free, no-pressure consultation.