Date: Monday, October 13
Time: 12-1pm
Location: Soda 510
Title: From Models to Agents: Building Reliable and Scalable AI Systems
Abstract:
This talk examines the transition from standalone language models to scalable agentic systems, focusing on three pillars of efficient deployment: latency, through cross-model communication in DroidSpeak (2024); resource efficiency, via workflow orchestration in Murakkab (2025); and accuracy, addressed in our forthcoming work Building Efficient and Reliable Agent Systems.
Bio:
Esha Choukse is a Principal Researcher at Microsoft in the Azure Research – Systems group. Her current research focus is on efficient AI in the cloud, spanning the layers of AI platforms, hardware, and datacenter design and provisioning. In the past, Esha has also worked on sustainability, memory systems, and compression. Esha has a PhD from University of Texas at Austin in computer architecture, and has published several papers at ISCA, ASPLOS, MICRO, HPCA, SC, and NSDI.