ML Compiler Engineer, TPU

Google is seeking an ML Compiler Engineer to join their ML, Systems, & Cloud AI (MSCA) organization. This role focuses on developing scaling, communication, and parallelization capabilities for XLA, the industry's leading ML compiler. The position involves working with Google's TPU platform, which powers all of Google's internal ML workloads and is widely used by external AI companies.

The role requires expertise in compiler optimization, low-level programming, and machine learning accelerator technologies. You'll be working on critical features that enable XLA to generate programs capable of running on thousands of TPU, GPU, or other accelerators. This is a unique opportunity to impact machine learning infrastructure at scale.

The position offers competitive compensation including a base salary range of $141,000-$202,000, plus bonus, equity, and comprehensive benefits. You'll be part of a team that designs, implements, and manages hardware, software, and ML infrastructure used by billions of Google users worldwide.

Key responsibilities include developing compiler parallelization features, implementing collective operations, optimizing compiler techniques, and building debugging tools. The ideal candidate should have experience with software development, compiler tools, and low-level ML accelerator programming.

This role is perfect for someone who wants to work at the intersection of machine learning and systems programming, contributing to technology that powers Google's most critical ML workloads and shapes the future of hyperscale computing. You'll be working with cutting-edge technology while having the opportunity to impact how billions of users interact with Google's services.