Hardware Functional Modeling SDE, AWS Machine Learning Accelerators

Join AWS's Annapurna Labs team as a Hardware Functional Modeling SDE working on cutting-edge machine learning accelerator chips. This role focuses on developing functional models for AWS's ML accelerator SoCs (System on Chips) that power their TRN and INF servers. As a senior engineer, you'll be responsible for creating end-to-end SoC functional models, collaborating with various teams including architecture, RTL design, and verification.

The position requires expertise in C++ programming and hardware modeling, with opportunities to work on large-scale systems that impact AWS's machine learning infrastructure. You'll be developing models that are crucial for both SoC verification and system software development, making your work essential to the product development lifecycle.

Key responsibilities include architecting and implementing functional models, improving model performance, and creating robust tooling for customers. While machine learning knowledge isn't required initially, you'll have the opportunity to learn and work with ML hardware systems. The role offers competitive compensation ranging from $129,300 to $223,600 based on location and experience.

You'll be working in either Cupertino, CA or Austin, TX, collaborating with a distributed team across both locations. The position offers the chance to work on innovative projects at the intersection of hardware and machine learning, with access to Amazon's comprehensive benefits package.

This role is ideal for someone with strong C++ skills, hardware modeling experience, and an interest in working on cutting-edge ML acceleration hardware. You'll be part of a team that's pushing the boundaries of machine learning hardware capabilities while building maintainable, scalable software solutions.

The position combines the stability of working for an industry leader with the excitement of developing next-generation ML acceleration technology. You'll have the opportunity to influence the direction of AWS's machine learning hardware infrastructure while working with some of the largest custom silicon deployments in the world.