Nvidia · posted · checked
Senior Power and Performance Engineer
C++LinuxPythonOn-site · ChinaSenior
Who can apply
On-site · China
Location: China, Shanghai
NVIDIA's Silicon Co-design Group (SCG) sits at a rare intersection: we own the full product development lifecycle, from early architecture definition through silicon bringup to product release. Our ArchDev team is the hub for silicon and system-level feature development, driving tradeoff analysis, system integration, and POR alignment across the entire organization. If you want to see your work go from whiteboard to world-class silicon, this is where that happens.
What You'll Be Doing:
Architect and integrate system-level performance and power management features, controllers, and policies to optimize product efficiency across datacenter and client products.
Build feature roadmaps to address low-power, low-noise, and performance-per-watt product needs through prototyping, use-case analysis, and cost/benefit trade-offs.
Partner with architecture, ASIC, board/platform, software/firmware, and marketing teams to drive design decisions and debug complex issues.
Track industry trends and market needs and translate them into forward-looking roadmaps that keep NVIDIA's products ahead of the curve.
Lead debug efforts, develop workarounds, and support bringup, validation, manufacturing, and customer escalations.
Utilize AI-driven techniques to enhance performance prediction models and power management strategies.
What We Need to See:
BS pr MS in EE/CE (or equivalent experience).
8+ years of experience with a strong focus of performance and power management on one or two of below areas that optimize power for perf-per-watt efficiency in datacenter or client systems: DVFS, power gating, clock policy, sequencing, throttling, control systems, boot/reset.
Strong EE fundamentals on digital design, low power design, DVFS, control systems, power management techniques, timing, and architecture.
Knowledge of PVT dependencies, binning methodologies, and VF characterization.
Solid understanding of firmware/driver structures and HW/SW interaction with different IPs, including their impact on power, latency, and reliability.