Software Engineer, ML Compilers, Silicon

Google is seeking a Software Engineer to join their ML Compilers team working on Google Tensor, the custom System-on-Chip (SoC) that powers Pixel phones. This role focuses on developing ML compilers for the Tensor TPU to accelerate Generative AI and other complex machine learning models running on custom hardware accelerators. The position combines cutting-edge machine learning, compiler development, and hardware optimization.

The ideal candidate will work at the intersection of machine learning and hardware acceleration, developing compiler solutions that efficiently map ML models to hardware while optimizing for performance, power consumption, and memory usage. They will collaborate closely with both ML researchers and hardware engineers to evolve and improve the compiler stack and future accelerator designs.

This is an opportunity to work on transformative technology that enables on-device AI experiences like Gemini Nano on Pixel phones. The role requires strong C++ programming skills, understanding of compiler technology, and the ability to balance various technical trade-offs. The position offers the chance to impact billions of users by making advanced ML capabilities accessible through Google's hardware products.

The team is part of Google's broader mission to organize the world's information and make it universally accessible. Working at Google provides the opportunity to solve complex technical challenges at scale while collaborating with world-class engineers and researchers. The role offers competitive compensation, comprehensive benefits, and the chance to work on cutting-edge technology that shapes the future of AI hardware acceleration.