ML Compiler Engineer, AWS Neuron, Annapurna Labs

AWS Neuron is seeking a talented ML Compiler Engineer to join their team working on cutting-edge products at the intersection of machine learning, high-performance computing, and distributed architectures. As part of Annapurna Labs, acquired by AWS in 2015, you'll work on the AWS Neuron SDK that optimizes neural net model performance on AWS Inferentia and Trainium custom chips.

The role involves developing and scaling a compiler to handle the world's largest ML workloads, working with AWS ML services teams, and contributing to pre-silicon design and new product features. You'll be part of the team that builds the compiler, runtime, and debugger integrated with major frameworks like TensorFlow, PyTorch, and MXNet.

This position offers the unique opportunity to work in a startup-like environment within AWS, focusing on infrastructure that powers AWS services. You'll collaborate with diverse teams across silicon engineering, hardware design, software, and operations. The team has delivered impressive products including AWS Nitro, ENA, EFA, Graviton, and ML accelerators.

The ideal candidate will bring strong technical capabilities and curiosity, with the ability to solve complex problems across the full software stack. While machine learning and AI accelerator experience is preferred, it's not required. You'll work in small, agile teams with significant autonomy to innovate and experiment.

The role offers excellent career growth opportunities through mentorship, knowledge sharing, and exposure to cutting-edge technology. AWS values work-life balance and fosters an inclusive culture with employee-led affinity groups and ongoing learning experiences. You'll be part of a team that embraces diverse perspectives and experiences while working on products that impact millions of customers worldwide.