Description
Vast.ai is hiring a full-time Systems/GPU Engineer to develop high-performance GPU kernels, tensor libraries, and auto-optimization tools for AI model inference. The role involves researching GPU programming and inference techniques, designing resource-management systems, evaluating novel architectures and methods, and collaborating with technical leadership. It is on-site in San Francisco or Westwood, Los Angeles, and requires C++/CUDA, GPGPU, Python, and Linux expertise.
