NVIDIA logo

Senior Power and Performance Engineer

NVIDIA
June 02, 2026
Full-time
On-site
Shanghai, SH, China
SoC Architecture Jobs, Level - Senior

Job Title

Senior Power and Performance Engineer

Role Summary

Work on system-level power and performance for datacenter and client silicon within the Silicon Co-design Group. The role architects power-management features, defines product-level policies, and supports silicon bringup and validation.

The engineer partners with architecture, ASIC, board, firmware/software, and product teams to optimize performance-per-watt and drive tradeoff decisions across product roadmaps.

Experience Level

Senior — typically 8+ years of relevant experience in power and performance engineering for silicon or system-level products.

Responsibilities

Primary responsibilities include:

  • Architect and integrate system-level power and performance features, controllers, and policies (e.g., DVFS, power gating, clock/sequencing, throttling).
  • Define feature roadmaps that balance low-power, noise, and performance-per-watt requirements through prototyping and trade-off analysis.
  • Collaborate with architecture, ASIC, board/platform, firmware/software, and product teams to influence design decisions and resolve cross-domain issues.
  • Lead debug and root-cause analysis during silicon bringup, validation, manufacturing, and customer escalations; develop workarounds as needed.
  • Use modeling, simulation, and data-driven techniques to predict performance and power under real workloads and guide architectural trade-offs.
  • Track industry trends and translate market needs into forward-looking power/performance roadmaps.

Requirements

Must-have technical skills and experience:

  • 8+ years of experience focused on power and performance management in datacenter or client systems.
  • Deep knowledge of DVFS, power gating, clock policy, sequencing, throttling, control systems, timing, and system architecture.
  • Understanding of PVT dependencies, binning methodologies, and VF characterization.
  • Solid familiarity with firmware/driver structures and HW/SW interactions that affect power, latency, and reliability.
  • Proficiency in one or more programming languages such as C/C++, Python, or Perl in Windows/Linux environments.
  • Strong problem-solving, cross-functional collaboration, and communication skills.

Nice-to-have:

  • Hands-on lab experience with oscilloscopes, multimeters, and logic analyzers; prior silicon bringup exposure.
  • Experience applying AI/ML to predict power/performance, automate data collection/analysis, or accelerate optimization workflows.
  • Experience with large-scale modeling and simulation tools and published research or patents in power management.
  • Demonstrated leadership aligning architecture, silicon, firmware, and software teams on complex problems.

Education Requirements

Bachelor's or Master’s degree in Electrical Engineering or Computer Engineering is specified; equivalent practical experience is explicitly accepted.


About the Company

Company: NVIDIA

Headquarters: Santa Clara, California, USA

NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.

NVIDIA logo

Date Posted: 2026-06-03