AI Computing Software Intern, GPU Kernel Libraries - 2027

Description du poste:

We are now looking for Compute/DL Architecture Performance Optimization Interns in our group! Are you passionate about exploring computer architectures for deep learning? Do you enjoy working at the intersection of hardware and software? NVIDIA is looking for world-class programmers and performance architects who like to continuously explore and mine the ultimate performance of each operator (or fusion operator) in deep learning networks, design and develop scalable modular infrastructure that can ship these highly optimized operators to different NVIDIA software libraries for training and inference.

What you'll be doing:
* Develop high performance operators on NVIDIA GPUs for cuBLAS, TensorRT, cuDNN, cuSparse and cuTensor libraries
* Analyze the performance of various GPU kernels on existing/new architecture, identify bottlenecks and propose creative solutions to improve them
* Design and develop software for kernel authoring and shipping
* Adopt cutting-edge AI technologies in GPU kernel or similar development workflow

What we need to see:
* Pursuing a B.S., M.S., or PhD degree in computer science (or similar)
* Strong programming skills in C/C++ and Python development
* Familiar with GPU programming model and CUDA
* Good understanding about compiler technologies and experience with LLVM and MLIR
* Excellent problem solving skills, good communication and teamwork

NVIDIA is widely considered to be one of the technology world's most desirable employers. We have some of the most forward-thinking and hardworking people in the world working for us. If you're creative and autonomous, we want to hear from you