Benchmarking LLM RAG Systems: a Real-World Hiring Use Case

Accepted talk for DevBcn 2026 about benchmarking RAG systems through a real-world hiring use case, comparing a Python LangChain implementation with a .NET Semantic Kernel implementation.

The session covers the end-to-end pipeline: dataset preprocessing, vector indexing, skill normalization, explainable responses, testing strategy, performance and latency comparison, and benchmark results from practical engineering trade-offs.