Silicon Systems Architect

Google•Apply•Published 9 days ago•First seen 9 days ago

Be part of a team that pushes boundaries, developing custom silicon solutions that power the future of Google's direct-to-consumer products. You'll contribute to the innovation behind products loved by millions worldwide. Your expertise will shape the next generation of hardware experiences, delivering unparalleled performance, efficiency, and integration.

As a System Architect, you will play a pivotal role in optimizing Google’s SoC performance for demanding AI and Android applications. You will drive the hardware strategy for the Pixel portfolio, leading the technical definition of future mobile and emerging concepts. By mapping desired user experiences to specific system workloads, you drive the hardware strategy from the ground up. You are responsible for establishing the compute topology and determining the optimal execution of workloads to ensure seamless end-to-end performance. You’ll collaborate with system performance and software teams to plan and conduct workload performance analysis, debug performance bottlenecks and project performance at various design phases. As the product moves into the productization phase, you will act as a technical anchor for the engineering teams. Your role involves validating architectural projections, supporting execution, and influencing key software and product feature decisions. You will remain involved at every critical checkpoint, ensuring the final product meets its power, performance and area goals.

Responsibilities

Advocate for a holistic system design by owning the end-to-end architecture, balancing compute distribution and data movement to align performance and power with user needs.
Lead deep-dive architectural investigations to identify bottlenecks and inefficiencies in current and future designs. Propose and validate innovative hardware-software co-optimization strategies that push the boundaries of system performance and power. Explore emerging technologies and architectural paradigms to define new opportunities for compute efficiency and feature enablement.
Author comprehensive system architecture specifications that map end-to-end data flows. You will clearly articulate how individual system components interact to deliver targeted user experiences.
Design and implement advanced system-level modeling frameworks and methodologies to accurately forecast power, performance and area. Use these projections to drive critical software optimizations and define the architectural specifications for next-generation hardware.
Drive post-silicon power characterization, optimization, and productization initiatives.

Minimum qualifications:

Bachelor's degree in Electrical Engineering, Computer Engineering, Computer Science, a related field, or equivalent practical experience.
10 years of experience in Convolutional Neural Network (CNN) data flows and their execution on Neural Processing Units (NPUs).
Experience in full software stack, including compilers, runtimes, and GPU/media processing pipelines.
Experience in Linux kernel scheduling and advanced power management strategies.

Preferred qualifications:

Master's degree or PhD in Electrical Engineering, Computer Engineering or Computer Science, with an emphasis on computer architecture.
Knowledge of ML benchmarks and workloads.
Understanding of AI Accelerators and Arm SME/SME2 Extension.