Description
NVIDIA is hiring a Compute Developer Technology software engineer to build and optimize parallel algorithms, data structures, GPU kernels, and communication libraries for large-language-model training and inference. The role involves optimizing operators and frameworks, improving distributed communication, analyzing application performance, and collaborating with architecture, research, libraries, tools, and system software teams. Candidates need an engineering or computer science degree or equivalent experience, at least two years of work experience, strong C/C++/Python/Fortran and parallel-programming knowledge, and experience with performance analysis and optimization in large-language-model or high-performance-computing contexts.
