Silicon AI/ML Architect, TPU, Google Cloud

As a Silicon AI/ML Architect, you will drive the Architecture of an AI/ML SoC and will support the engineering teams during the implementation and validation phases, pre-silicon, and post-silicon. You will work closely with internal system teams and external partners to develop a comprehensive understanding of the required SoC functions given its surrounding hardware, software, and the economic environments. You will also collaborate with the Engineering teams to drive the optimal balance between performance, features, power, schedule, and cost. You will be responsible for developing SoC architecture and Architecture specifications that meet current and future computing requirements for AI/ML roadmap, evaluating different silicon solutions for executing Google’s data center AI accelerator roadmap: off-the-shelf components, vendor co-developments, custom designs, and chiplets. You will also collaborate closely with Systems and Software teams to create high performance hardware/software interfaces. You will work with design, verification, emulation, physical design, packaging, and silicon validation stakeholders to ensure that designs are complete, correct, and performant. You will evaluate power, performance, area tradeoffs and drive improvements across generations.