Staff Software Engineer, ML Compilers, TPU

Experteer Overview In this role you will contribute to the XLA compiler, enabling TPU workloads and accelerating ML and scientific computing at scale. You will work with cross-functional teams to optimize and extend the compiler stack for new hardware generations, workloads, and models. You’ll influence hardware/software co-design and push performance across distributed systems. This is a hands-on role with impact on Google Cloud and internal users, offering opportunities to shape next-gen AI infrastructure. Compensation / Benefits * Develop and optimize compiler passes to extract performance on current and next-gen TPUs * Collaborate with hardware designers on HW/SW co-design for accelerators * Target and compile high-performance ML operations at large scale * Support new workloads, models, and TPU hardware generations * Work across the compiler stack and with end-user ML models to improve efficiency Tasks * Bachelor’s degree or equivalent practical experience * 8 years programming in C++ or Python * 5 years testing and launching software products * 5 years of experience with performance, large-scale systems data analysis, visualization tools, or debugging * 3 years of software design and architecture Key requirements * bonus target * equity * benefits

Experteer Overview In this role you will contribute to the XLA compiler, enabling TPU workloads and accelerating ML and scientific computing at scale. You will work with cross-functional teams to optimize and extend the compiler stack for new hardware generations, workloads, and models. You’ll influence hardware/software co-design and push performance across distributed systems. This is a hands-on role with impact on Google Cloud and internal users, offering opportunities to shape next-gen AI infrastructure. Compensation / Benefits * Develop and optimize compiler passes to extract performance on current and next-gen TPUs * Collaborate with hardware designers on HW/SW co-design for accelerators * Target and compile high-performance ML operations at large scale * Support new workloads, models, and TPU hardware generations * Work across the compiler stack and with end-user ML models to improve efficiency Tasks * Bachelor’s degree or equivalent practical experience * 8 years aaaaaaaaaf _ in C++ or Python * 5 years testing and launching software products * 5 years of experience with performance, large-scale systems data analysis, visualization tools, or debugging * 3 years of software design and architecture Key requirements * bonus target * equity * benefits