We will involve you in profiling, benchmarking, and optimizing AI training and inference workloads using ROCm, PyTorch, JAX, vLLM, Triton, and related performance engineering tools, helping identify bottlenecks across compute, memory bandwidth, communication, and kernel execution. We will train you to analyze and optimize end-to-end AI workflows, including large language models (LLMs) and generative AI applications, exploring techniques such as model optimization, operator fusion, scheduling strategies, mixed precision, and quantization.