Software Engineer, GPU Performance
Toronto, ONHeyGen
Candidates need experience optimizing GPU-based AI or high-performance computing systems, strong Python and PyTorch skills, and knowledge of GPU hardware. Using profiling tools to validate improvements is required. CUDA, Triton and video or diffusion model experience are preferred.
PyTorch, NVIDIA Nsight Systems, NVIDIA Nsight Compute, PyTorch Profiler, CUDA, Triton