Silicon AI/ML Architect, TPU, Google Cloud

Responsibilities

• Develop SoC architecture and Architecture specifications that meet current and future computing requirements for AI/ML roadmap.
• Evaluate different silicon solutions for executing Google's data center AI accelerator roadmap: off-the-shelf components, vendor co-developments, custom designs, and chiplets.
• Collaborate with Systems and Software teams to create high performance hardware/software interfaces.
• Collaborate with design, verification, emulation, physical design, packaging, and silicon validation stakeholders to ensure that designs are complete, correct, and performant.
• Evaluate power, performance, area tradeoffs and drive improvements across generations.

Minimum qualifications:

• Bachelor's degree in Electrical Engineering, Computer Engineering, Computer Science, a related field, or equivalent practical experience.
• 10 years of experience in architecture of machine learning or graphics SoCs.
• 8 years of experience with performance, power, area, cost tradeoff analysis for multi chiplet SoC architectures.
• Experience with ASIC design flows, from specification to production.

Preferred qualifications:

• Experience in SoC designs, RTL coding and integration flows.
• Experience working with software teams optimizing the hardware/software interface.
• Experience in estimating performance by analysis and modeling, and experience in defining and driving performance test plans.
• Experience in a procedural programming language (e.g., C++, Python, Go).
• Knowledge of high performance and low power design techniques.
• Knowledge of arithmetic units, bus architectures, accelerators, or memory hierarchies.