1 sessions
- Breakout sessionAI/MLHybrid CloudFinancial ServicesGovernmentManufacturing & IndustrialDigital SovereigntyEdge ComputingGenerative AI300 – AdvancedDeveloper / EngineerIT Professional / Technical ManagerSolution / Systems ArchitectCaesars ForumAmazon Elastic Compute Cloud (Amazon EC2)AWS Local ZonesAWS OutpostsSilent session10:00 a.m. Monday, Dec 02Monday, Dec 02Customers in regulated industries are looking to leverage generative AI with sensitive data that must remain on premises due to data residency requirements. Additionally, some customers with data generated at the edge need to run small language models (SLMs) locally for real-time processing. This session explores how to select, fine-tune, and deploy SLMs for on-premises and edge use cases using AWS hybrid and edge services. Learn how to run Retrieval Augmented Generation (RAG) with on-premises data to improve prompt outcomes. Understand model trade-offs across accuracy, performance, and cost efficiency, and discover architectural best practices for security, scalability, and high availability.
, Principal Specialist and SA Manager, Telco/Hybrid Edge, AWS
, WWSO SSA, AWS
, Outposts Solutions Architect, Amazon Web Services
- Monday, Dec 210:00 AM - 11:00 AM PSTCaesars Forum | Level 1 | Summit 232 | Content Hub | Pink Screen