We are seeking a GPU Kernel and Performance Engineer to make our research models run fast on real hardware, primarily NVIDIA GPUs... such as CUTLASS and CuTe. Experience with multi-GPU communication (e.g. NCCL, NVLink). An understanding of LLM inference performance...
and quantization, and serving at scale with vLLM, SGLang or TensorRT-LLM, ideally on AWS and including GPU kernel work (CUDA or Triton... customers stop threats faster and fix what matters most. About the Role As a Senior Principal AI Engineer, you will set the...
filesystems, job schedulers, GPU tooling, fleet automation, and low-level kernel work. Much of what we run does not exist off the...). Python for scripting. 5–10 years building large-scale distributed systems at production scale. Deep Linux expertise...