This session walks through a production RAG system that turns a pile of unstructured resumes into a searchable, rankable talent pool. We cover the full pipeline, from ingestion to retrieval to grounded answers with Claude, and focus on the engineering decisions that actually matter when you move from a weekend prototype to something reliable in production.

Audience Takeaways:

- How to design an ingestion pipeline for real-world, semi-structured documents.
- Why retrieval strategy matters more than model choice for search quality.
- How to tune OpenSearch for the right balance of speed and accuracy.
- Where an LLM genuinely adds value on top of retrieval, and where it just adds cost