Drive end-to-end performance leadership for AI/ML workloads, including workload selection, characterization, simulation, performance projection, root-cause analysis, and attainment across pre-silicon and post-silicon phases, partnering closely with Architecture, Software, Hardware Engineering, and Product teams. Recognized leader in AI/ML performance engineering with hands-on experience in LLM, generative AI, and large-scale training/inference workloads across GPU-accelerated systems, including performance modeling, benchmarking, and architecture evaluation.