ML Accelerator Architect and Performance Engineer, Silicon

This role involves developing custom silicon solutions for Google's direct-to-consumer products. As an ML Accelerator Architect and Performance Engineer, you'll focus on exploring future hardware and software architectures for efficient on-device machine learning applications. This includes hardware architecture exploration, contributing to compiler, runtime, and API strategies, and collaborating with research teams, system architecture teams, and compiler engineers to optimize workloads. Responsibilities include driving hardware architecture exploration, initiating feature modeling in architecture simulators, optimizing performance, collaborating with researchers and application developers, enhancing user experiences by partitioning ML workloads, and engaging with other Google engineers and researchers.