Sai Saketh is an AI Performance Engineer at Red Hat, where he focuses on understanding and optimizing the performance of AI workloads and infrastructure.

He earned his Master of Science in Mathematics and Computer Science from Sri Sathya Sai Institute of Higher Learning in April 2026. As part of his graduate research, Saketh spent nearly a year benchmarking Llama 3.1-8B on NVIDIA H200 GPUs using MLPerf inference workloads, systematically tuning vLLM configurations and analyzing Nsight Systems traces to uncover performance bottlenecks.