Description
Amazon is hiring a senior software engineer to architect and implement distributed inference support for PyTorch in the AWS Neuron SDK, optimizing large language model families on Trainium and Inferentia hardware. The role covers model enablement, performance profiling, kernel and system-level optimization, testing, production deployment, customer collaboration, and mentoring experienced engineers. It requires a bachelor's degree, at least five years of professional software development experience, strong C++ and Python skills, and expertise in machine learning, distributed systems, parallel computing, and low-level optimization.
