Description
NVIDIA is hiring a Performance Software Intern for Deep Learning Libraries to develop optimized GPU code for linear algebra and deep learning operations. The intern will write highly tuned compute kernels, support regression testing and CI/CD, and collaborate with compiler, deep-learning performance, hardware, and architecture teams. The role requires a master’s or PhD in a relevant field, strong programming and software-design skills, experience with performance-oriented parallel programming, computer-architecture knowledge, and assembly-programming experience.
