Software Engineer - Hardware Abstraction Layer, AWS Machine Learning Accelerators

AWS is seeking talented engineers to join their system software team developing the hardware abstraction layer (HAL) for cutting-edge machine learning accelerators. This role is part of AWS's Annapurna Labs organization, which designs and deploys some of the largest custom silicon in the world. The position focuses on developing critical infrastructure management software for AWS's machine learning servers (Trainium and Inferentia).

The role requires expertise in C++ programming and hardware systems, working at the lowest level of AWS infrastructure to ensure chip functionality, performance, and security. You'll collaborate with hardware designers and system software teams to build HALs for new SoC IPs, solve architectural challenges, and innovate on cross-functional solutions.

This is an exciting opportunity to work with thought-leaders in multiple technology areas, building the future of machine learning infrastructure. The team operates with a startup-like mentality within AWS, focusing on fast-paced development and innovation. While the role involves working with ML chips, no machine learning background is required as the focus is on low-level system software development.

The position offers competitive compensation, comprehensive benefits, and significant growth opportunities. AWS values diversity, work-life harmony, and maintains an inclusive culture with various employee-led affinity groups. The team supports knowledge-sharing and mentorship, making it an ideal environment for professional development.

Based in either Cupertino, CA or Austin, TX, you'll be part of a team split between both locations, working on challenging problems that push the boundaries of what's possible in cloud computing and machine learning acceleration.