Silicon Architect, AI and Infrastructure

Google•Sunnyvale, CA

3d•$240,000 - $333,000

About The Position

As a Silicon Product Architect within the Cloud Silicon Engineering team, you will lead end-to-end product architecture for next-generation systems and chips, helping shape TPU technology for demanding AI/ML applications. You will connect machine-learning workloads, system software, and silicon implementation to define accelerator products for Google’s technical infrastructure and Cloud AI customers. You will own product-level architectural definition from initial concept and pathfinding through specification, silicon execution, and production deployment. Working with machine-learning researchers, compiler and systems software engineers, customers, and cross-functional silicon leads, you will help ensure architectures meet goals for functionality, performance, power, area, cost, reliability, usability, and deployability. The role also involves setting technical direction across product subsystems and partnering across silicon development phases to deliver production-ready hardware and software stacks.

Requirements

Bachelor's degree in Electrical Engineering, Computer Engineering, Computer Science, a related field, or equivalent practical experience.
15 years of experience in computer architecture.
Experience with high-performance computing (HPC), server processors, GPUs, or machine-learning accelerators.

Nice To Haves

Master's degree or PhD in Electrical Engineering, Computer Engineering, or Computer Science.
Experience with semiconductor technologies and system-level trade-offs across process nodes, memory subsystems such as HBM/DRAM, interconnects, packaging, and power/performance/area (PPA).
Experience as the lead product or chip architect across multiple generations of complex data-center AI/ML accelerators, GPUs, or HPC silicon.
Experience driving cross-functional technical alignment across RTL design, physical implementation, verification, thermal/power engineering, and post-silicon validation teams.
Strong track record of technical influence, mentoring architects, and translating emerging academic and industry AI trends into multi-year silicon product roadmaps.

Responsibilities

Drive the end-to-end silicon product architecture and roadmap for next-generation accelerators in collaboration with internal AI/ML research teams, software and systems teams, and customers, maintaining a rigorous hardware-software co-design process.
Define and own product-level chip architectures and top-level specifications, ensuring products meet goals for functionality, performance, power efficiency, die area and cost, reliability, usability, and fleet deployability.
Lead architectural pathfinding, trade-off studies, and assessments of emerging AI workloads and semiconductor technologies.
Set technical direction across key product subsystems to enable rapid and predictable execution of complex server-class ASICs.
Partner across all phases of silicon development and with compiler and runtime teams to resolve cross-domain bottlenecks and deliver production-ready hardware/software stacks.