Description
NVIDIA is hiring a Deep Learning Performance Software Engineering Intern to support research and development of GPU-accelerated deep learning software. The intern will create and maintain SKILL, Wiki, and agent harnesses; develop TileGym, Triton CUDA TileIR backend, and CUDA Tile; create highly optimized tile-based GPU kernels; and perform end-to-end performance optimization, analysis, and tuning. The role requires an engineering or computer science degree in progress, strong C/C++ and software design skills, knowledge of agentic systems, and experience or knowledge of performance modeling, profiling, debugging, and CPU or GPU architecture.
