Make Your GPU Earn Its Keep: A Kernel Engineering Deep Dive

AI Performance Engineering Meetup (San Francisco, Global) Monday, November 30, 2026 · 9:00–10:00 AM PST · Online Zoom link: https://us02web.zoom.us/j/82308186562 A powerful GPU can spend plenty of time waiting. What is it waiting for—and how do you find out? Talk #0: Welcome and Meetup Updates by Chris Fregly and Antje Barth Talk #1: From “Why Is This Slow?” to a Faster Kernel by Dr. Rajat “Raj” Dandekar, Co-founder of Vizuara Join Raj for a focused tour of the engineering behind fast AI kernels, drawing on Vizuara’s Kernel Engineering course on Maven. We’ll connect the roofline model to CUDA execution and the GPU memory hierarchy, then look at how profiling guides optimizations such as coalesced memory access, tiling, and tensor-core use. Matrix multiplication and attention provide context for seeing how those ideas fit together in modern AI workloads, including FlashAttention. The goal is a practical way to decide what to measure, which bottleneck matters, and whether an optimization helped. The session is dedicated to Raj’s talk, with time for audience questions. Who it’s for: Engineers comfortable with Python or basic PyTorch. Prior CUDA or C++ experience is not required. Bio: Dr. Rajat Dandekar is a co-founder of Vizuara and a Kernel Engineering course instructor. He holds a PhD in Mechanical Engineering from Purdue University and BTech and MTech degrees from IIT Madras. Based on: Kernel Engineering: From CUDA Foundations to Frontier AI Kernels (https://maven.com/rajat-dandekar/kernel-engineering) Scheduling note: November 30 is the proposed new date; speaker confirmation is pending. Zoom link: https://us02web.zoom.us/j/82308186562 Related Links Github Repo: http://github.com/cfregly/ai-performance-engineering/ O’Reilly Book: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/ YouTube: https://www.youtube.com/@AIPerformanceEngineering Generative AI Free Course on DeepLearning.ai: https://bit.ly/gllm