CUTLASS GPU Performance Engineer - Kernel Benchmarking

NVIDIA is seeking an experienced professional to join the CUTLASS team, focusing on benchmarking and optimizing deep learning model performance. This role requires strong programming skills in Python and C++, with experience in software performance analysis and optimization. The ideal candidate holds a Master's or PhD in Computer Science and has over 3 years of relevant experience. The position offers a competitive salary determined by location and experience, along with equity and benefits. #J-18808-Ljbffr