Description
NVIDIA is seeking an Accelerated Computing Architect intern to analyze and optimize performance on current and next-generation GPUs, study hardware-software interactions, support software-hardware co-design, and collaborate with hardware, software, product, and research teams. The intern will also document and present work through white papers, conference publications, blog posts, and patent applications. The role requires a relevant B.Sc., M.Sc., or Ph.D., strong GPU and computer systems knowledge, C and C++ proficiency, and experience with massively parallel GPU programming models such as CUDA or OpenCL.
