ML Kernel Performance Engineering Manager

Annapurna Labs (U.S.) Inc. is seeking kernel engineers to optimize ML workloads on AWS accelerators. You will design high-performance compute kernels for Neuron, analyze multi-generation performance, and implement compiler optimizations in collaboration with compiler, runtime, framework, and hardware teams. The role involves working at the hardware-software boundary, mentoring engineers, publishing research, and interfacing with customers to enable model acceleration on Inferentia and Trainium #J-18808-Ljbffr