2024 will see a record amount of GenAI applications in production.

This also means 2024 will see a lot of investment go into AI infrastructure and pipeline optimization.

AI Engineers are going to be at the center of it all.

This talk provides you with the mindset and tools to get ahead of the curve and begin implementing RAG (Retrieval Augmented Generation) system optimization and performance improvement components in your application today!

We’ll cover essential components of the RAG pipeline, emphasizing actionable strategies for enhancing system performance.

Key topics include practical chunking strategies, context enrichment for accuracy, prompt compression for query optimization, and efficient document retrieval methods. The focus is on reducing latency, minimizing costs, and improving operational efficiency.

Attendees will leave with a toolkit of optimization strategies to apply directly to their RAG systems, driving significant performance improvements. This presentation targets AI Engineers and Developers managing RAG systems, offering a deep dive into effective optimization techniques.