Senior AI Engineer

Design and ship LLM-powered features — RAG pipelines, agents, and prompt-driven workflows — for client products end to end.

What you'll do

• Build and evaluate retrieval-augmented generation pipelines for production use
• Design agent workflows using OpenAI, Claude, Gemini, and local models
• Own prompt versioning, testing, and evaluation practices
• Collaborate directly with client stakeholders on scope and architecture

What we're looking for

• 3+ years building production ML or LLM-backed systems
• Strong Python fundamentals; comfortable with vector databases
• Experience shipping features behind real user traffic, not just prototypes
• Clear written communication for client-facing work