About this role
Research Engineer - CUDA Kernel Engineering at Voltai. Location: Palo Alto, California, United States. Role: develop kernels, profile performance, integrate kernels Requirements: Experience writing and optimizing CUDA kernels, GPU performance profiling, integrating kernels into PyTorch/Megatron, and working with NVIDIA hardware. Category: Research and Development (R&D) Seniority: Mid Level Tools: CUDA, PyTorch, Megatron-LM, vLLM, TorchTitan, NCCL, Triton Commitment: Full Time Workplace: Onsite Languages: English