Optimizing Generative AI Systems with AWS and Snorkel

Learn how to streamline Generative AI development through programmatic data labeling and scalable infrastructure in this comprehensive webinar from Snorkel AI and AWS. Discover effective methods for integrating Snorkel Flow with AWS Bedrock and SageMaker to enhance LLM performance, improve Retrieval-Augmented Generation (RAG) workflows, and accelerate GenAI deployment. The session includes a detailed demonstration of Snorkel Flow working with AWS services, a deep dive into integration techniques, strategies for scaling GenAI workflows in production environments, and a live walkthrough of RAG optimization. Explore advanced optimization techniques, examine performance improvements achieved through the Snorkel and AWS partnership, and review enterprise use cases for GenAI systems, concluding with audience Q&A.

Syllabus

00:00 – Introduction & Agenda
01:17 – Overview of AWS GenAI Tools
04:04 – Retrieval-Augmented Generation RAG Optimization
07:09 – Demo: Snorkel Flow + AWS
13:34 – AWS + Snorkel Integration Deep Dive
20:33 – Scaling GenAI Workflows in Production
29:49 – Live Walkthrough: Optimizing RAG with Snorkel
38:01 – Advanced Techniques in GenAI Optimization
45:14 – Snorkel + AWS Performance Gains
52:34 – Final Thoughts on RAG Optimization
58:54 – Enterprise Use Cases for GenAI Systems
01:08:54 – Q&A and Closing Remarks