Description
The role focuses on developing and optimizing machine-learning systems for AMD GPUs and ROCm, including designing new machine-learning technologies, supporting Linux, working with C/C++ and Python, writing GPU kernels and shaders, debugging with tools such as gdb and valgrind, and profiling ROCm and CUDA kernels. It requires a computer science degree, strong programming and Linux skills, knowledge of Python machine-learning frameworks, GPU architecture, and experience with AI models and inference engines.
