Description
Vast.ai is hiring a full-time Systems Engineer to scale AI inference by designing and optimizing GPU kernels and tensor libraries, translating HPC techniques into scalable inference solutions, evaluating emerging architectures and resource-management approaches, and improving GPU infrastructure efficiency. The role requires CUDA/C++, GPGPU, Python, and Linux, with advanced C++, parallel programming, systems optimization, and HPC performance tooling experience preferred. It is on-site in San Francisco or Westwood, Los Angeles, and includes health, dental, vision, life insurance, a 401(k) match, equity, and onsite meals.
