Senior ML Compiler Engineer, Silicon

Google is seeking a Senior ML Compiler Engineer to join their Silicon team, focusing on developing cutting-edge Machine Learning (ML) compilers for the Tensor TPU to accelerate Generative AI and other complex machine learning models running on custom hardware accelerators. This role sits at the intersection of machine learning, compiler optimization, and hardware acceleration.

The position requires deep expertise in compiler development, with a specific focus on ML applications. You'll be working on critical projects that directly impact Google's ML infrastructure, particularly in the domain of always-on computing use cases. The role involves mapping ML models to hardware Instruction Set Architecture (ISA), optimizing for various performance metrics, and collaborating closely with both ML researchers and hardware engineers.

As part of Google's mission to organize the world's information and make it universally accessible, you'll be working with a team that combines the best of Google AI, Software, and Hardware to create radically helpful experiences. The team focuses on researching, designing, and developing new technologies to make computing faster, seamless, and more powerful.

Key responsibilities include building and optimizing compilers for ML workloads, evaluating parallelization strategies, and productizing various ML workloads on the Pixel Edge TPU. You'll be working with cutting-edge technologies like Gemini Nano and various ML models for camera, imaging, and speech applications.

The ideal candidate should have at least 5 years of experience with compilers and 3 years of experience in software product development. Strong technical expertise in compiler optimization, machine learning, and hardware architecture is essential. This role offers the opportunity to work on next-generation technologies that will impact billions of users while pushing the boundaries of ML compiler optimization and hardware acceleration.