CoreWeave is seeking a Senior Engineer for its Benchmarking & Performance team to own kernel-level optimization for LLM inference and end-to-end model serving, focusing on CUDA kernels and throughput/latency improvements.
You will lead kernel design reviews, mentor engineers, and drive reproducible benchmarking across vLLM, TensorRT-LLM, and related stacks while partnering with product, orchestration, and hardware teams.
#J-18808-Ljbffr