Tensor SOC Performance Design Verification Engineer

Minimum qualifications:

• Bachelor's degree in Electrical Engineering, Computer Engineering, Computer Science, or a related field, or equivalent practical experience.
• 5 years of experience with verification methodologies and languages such as UVM and SystemVerilog.
• Experience in mobile SOC performance model development, performance analysis, and workload characterization.
• Experience verifying digital logic at the Register Transfer Level (RTL) using SystemVerilog at Subsystem or Full chip level.
• Experience in performance and latency architecture for an ARM based SOC.
• Experience in performance measurement and debugging in an emulation environment.

Preferred qualifications:

• Master's degree or PhD in Electrical Engineering, Computer Engineering or Computer Science, with an emphasis on computer architecture.
• Experience in microarchitecture innovation.
• Experience in low-power design verification.
• Knowledge of CPU, GPU benchmark characterization.
• Knowledge of system software components, such as Linux, drivers, and runtime.
• Knowledge of performance analysis tools.

Google's mission is to organize the world's information and make it universally accessible and useful. Our team combines the best of Google AI, Software, and Hardware to create radically helpful experiences. We research, design, and develop new technologies and hardware to make computing faster, seamless, and more powerful. We aim to make people's lives better through technology.

• Develop simulators and architectural models of Google's Tensor SOC.
• Collaborate with system architects, SoC and CPU/GPU/TPU architects/designers, and software and application experts to understand current and future requirements.
• Participate in architectural and design evaluation of Tensor SOC features studies.
• Perform pre-silicon performance simulation and correlate with pre and post-silicon measurements.
• Communicate analysis results qualitatively and quantitatively.