triton , inference paths, performance profiling, Benchmarking, CK, AITER, AMD GPU, ML kernels, ROCm, hip, quantization methods, kernel technologies

Python, evaluation methodologies, ML fundamentals, inference pipelines, large-scale datasets, distributed training, CPT post-training, LLM frameworks, LLM architectures, tuning techniques

Jax, Pytorch, Python, Production ML systems running on GPUs