Machine Learning Engineer, AWS Neuron Inference, Annapurna ML

Job description

AWS Neuron is the complete software stack for the AWS Inferentia and Trainium cloud-scale machine learning accelerators and the Trn2 and future Trn3 servers that use them. This role is for a software engineer in the Machine Learning Applications (ML Apps) team for AWS Neuron. This role develops, enables and performance tunes building blocks for all key ML model families, including Llama3, GPT OSS, Qwen3, DeepSeek and beyond. The Neuron Inference Technology team works side by side with the Inference Model Enablement, compiler runtime engineers to create, build and tune high-performance distributed inference solutions for the latest generation Trainium accelerators. Experience optimizing LLM inference performance with kernels, Python, PyTorch or JAX is a must. Key job responsibilities This team develops optimized building blocks for the Neuron distributed inference library, tuning them to ensure highest performance and maximize efficiency running on Trn2 and Trn3 servers. A day in the life As you develop technology components, you’ll create metrics, implement automation and other improvements, and resolve the root cause of software defects. You’ll also participate in design discussions, code review, and communicate with internal and external stakeholders. You will work cross-functionally with teams across Neufon in a fast-paced startup-like development environment, where…