Senior AI/ML Inference Engineer for Custom AWS Neuron

Amazon is hiring a Senior Software Development Engineer for AI/ML workloads on AWS Neuron to accelerate inference on Inferentia and Trainium accelerators. You will design, implement, and optimize ML models and kernels across the stack, from PyTorch to hardware-bound performance, and mentor engineers in a startup-like, fast-paced team.

You will collaborate with cross-functional teams, analyze system performance, and contribute to architecture design for state-of-the-art Generative AI workloads,