Description
AWS Neuron is hiring a Senior Software Engineer for its Machine Learning Applications team to build distributed inference support for PyTorch and optimize machine learning models on Amazon’s Inferentia and Trainium accelerators. The role covers distributed computing architecture, performance profiling, low-level optimization, kernel development, memory and parallel computing, and production deployment, with collaboration across compiler, runtime, framework, hardware, and customer teams. Candidates need a bachelor’s degree, at least five years of professional software development experience, strong Python and C++ knowledge, and experience with system architecture, performance optimization, and large-scale systems.
