Software Engineer II - AI/ML, Neuron Inference, Inference

What you’d do

Build and optimize distributed inference support for PyTorch in the Neuron SDK and tune models to run efficiently on AWS Trainium accelerators. Work spans compiler, runtime, framework, and hardware teams on low-level optimization and ML model acceleration. Full-time in Cupertino, California. Found on the employer's careers page on Oct 14, 2026. Apply through the link.

You’ll need

• 3+ years non-internship professional software development experience
• Bachelor's degree or foreign equivalent in Computer Science, Engineering, Mathematics, or related fi
• Python and/or C++ programming
• System-level programming
• Machine learning knowledge