Elevate high-performance computing as a Senior Staff Software Development Engineer specializing in GPU libraries. Engage in collaborative efforts to optimize AI and machine learning resources at Exascale.
This role focuses on improving math and communication libraries as part of the AMD ROCm platform. You will work closely with agile teams to test libraries on the latest GPUs while ensuring the highest code quality. Your ability to benchmark and profile performance will be crucial in driving optimizations across multi-GPU systems.
Key Responsibilities:
• Test new ROCm libraries on AMD hardware
• Analyze issues with development teams
• Conduct comprehensive code quality evaluations
• Optimize performance for multi-GPU implementations
• Collaborate with experts to refine applications
Requirements:
• Proficiency in C, C++, and assembly
• Understanding GPU architecture with HIP or CUDA
• Experience with debugging on early hardware
• Skills in automated t...