Staff Software Engineer at LinkedIn, Seattle, Washington, USA

Title of the Talk :
Mastering Retrieval-Augmented Generation (RAG): Scaling Generative AI with Real-Time Knowledge

Abstract of Talk:
Large Language Models (LLMs) have revolutionized how we generate and interact with text, but they come with critical limitations: hallucinations, stale information, and brittle domain knowledge. Retrieval-Augmented Generation (RAG) is a practical, production ready approach that addresses these gaps by combining the power of generative models with real-time retrieval from trusted knowledge bases.
In this keynote, we will demystify RAG from the ground up. You’ll learn why leading AI teams rely on RAG to make LLMs more factual, more explainable, and easier to adapt. without the cost and complexity of constant model retraining. We’ll unpack RAG’s architecture step by step, explore real-world examples from enterprise chatbots to research copilots, and share practical lessons from building and deploying RAG pipelines at scale.
This session is for AI engineers, architects, and technical leaders who want to move beyond the hype and understand how retrieval + generation unlocks the next level of trustworthy, domain-specific AI systems.