Senior ML Kernel Performance Architect

Amazon's Annapurna Labs team seeks a senior kernel engineer to design high-performance ML compute kernels for Neuron on Inferentia and Trainium accelerators. You will optimize across compiler, runtime, and hardware stacks and mentor a team of engineers.

You'll collaborate with customers and cross-functional groups to push the boundaries of ML acceleration, delivering scalable kernels and libraries that maximize performance on AWS AI workloads.