ML Compiler Software Engineer PEY Co-op (12-16 months), Annapurna ML

AWS Neuron is seeking talented student engineers to join their compiler team working on cutting-edge deep learning acceleration. As part of the team developing the Neuron SDK, you'll work on optimizing performance of neural net models for AWS Inferentia and Trainium custom chips. The role involves working with a compiler stack that integrates with major frameworks like TensorFlow, PyTorch, and MXNet.

This 12-16 month co-op position offers hands-on experience in compiler development, deep learning infrastructure, and performance optimization. You'll be mentored by experienced engineers while implementing critical features that help democratize access to ML acceleration. The work directly impacts AWS customers running production ML workloads.

The ideal candidate has strong programming fundamentals in languages like Python, Java or C++, and academic background in areas like compiler optimization, algorithms, and machine learning. You'll gain exposure to the complete ML infrastructure stack - from frameworks to hardware.

This is an excellent opportunity for students interested in systems software, compilers, and machine learning to gain real-world experience working on AWS's custom silicon initiative. You'll be part of a team pushing the boundaries of ML acceleration while learning from industry experts in a collaborative environment.

The position is based in Toronto and requires a 12-16 month commitment starting May 2025. AWS offers comprehensive benefits and the chance to work on technology that powers many of the world's leading ML applications. Join us in making deep learning more accessible and cost-effective for developers worldwide.