Leads performance experiments on AI training, inference, and agentic workloads across multi-GPU server systems. Profiles memory, storage, interconnect, power, and thermal behavior from GPU memory through cluster scale. Develops performance models, simulations, traces, and benchmarking tools; evaluates memory tiering, KV-cache management, data placement, and migration. Converts findings into product requirements, engineering recommendations, publications, demonstrations, and customer guidance while leading cross-functional initiatives.