AI/ML Engineer

Design RAG pipelines: chunking, embeddings, vector search, and re-ranking

Build agentic workflows with tool use over client systems and APIs

Create evaluation harnesses — accuracy, latency, and cost dashboards

Fine-tune or adapt open models where APIs don't fit the constraint

Ship everything behind clean APIs with monitoring and guardrails

Requirements

2+ years of production Python plus real LLM project experience

Hands-on with embedding models and at least one vector store

Understanding of context management, token budgets, and eval design

Pragmatism: the best model is the one that ships within budget