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...
engineering robust inference pipelines, establishing comprehensive performance metrics, and identifying and resolving bottlenecks..., efficient, and scalable performance across real-world applications. You will work on a wide spectrum of systems, ranging...
and quantization, and serving at scale with vLLM, SGLang or TensorRT-LLM, ideally on AWS and including GPU kernel work (CUDA or Triton...Our Engineering organisation is scaling its AI Engineering capabilities under new leadership, creating an opportunity...
- and syscall-level debugging experience and performance engineering craft Experience profiling or instrumenting accelerator... the monitoring and telemetry infrastructure that every engineer and researcher at Anthropic depends on-from metrics...
. You will join a small research team, working with our Research Software Engineer and kernel engineer, and take early-stage ideas through... and development process. We also value: GPU kernel work (e.g. Triton, CUDA) for sparse or custom attention. Experience...