Hardware Modeling Simulation SDE, AWS Machine Learning Accelerators

Amazon Web Services (AWS) is seeking a Hardware Modeling Simulation Software Development Engineer to join their Machine Learning Accelerators team. This role focuses on building functional models of ML accelerator chips that power AWS's Machine Learning Acceleration servers (TRN and INF). The position involves developing C++ models, infrastructure, and tooling to speed up SoC verification and system software development.

The role is based within Annapurna Labs, an AWS organization that designs and deploys some of the world's largest custom silicon. You'll be working on critical software used in both SoC development and by partner software teams. The position requires expertise in functional modeling for SoCs, ASICs, TPUs, GPUs, or CPUs, along with strong C++ programming skills using object-oriented principles.

This is an opportunity to work at the intersection of hardware and machine learning, though prior ML experience is not required. The role offers the chance to collaborate with multiple teams, influence product development, and contribute to the future of machine learning infrastructure at AWS. The position can be based in either Cupertino, CA or Austin, TX.

Key responsibilities include developing end-to-end SoC functional models, collaborating with various engineering teams, improving model performance, and creating maintainable, well-documented software. The ideal candidate will be passionate about learning new technologies, building scalable software, and working in a fast-paced environment as part of a small team within AWS's larger organization.

The compensation package includes a competitive base salary ranging from $129,300 to $223,600 depending on location, plus equity, sign-on payments, and comprehensive benefits including medical coverage and 401k. This is a unique opportunity to join a team that's pushing the boundaries of machine learning hardware and modeling capabilities at one of the world's leading technology companies.