GPU Power & Performance Systems Engineer

NVIDIA Corporation; Santa Clara (CA); On-site; USD 124,000 - 242,000; Full time

Job summary

NVIDIA Corporation is seeking a System Software Engineer to join the GPU Performance and Power Management Software team in Santa Clara, CA. You will design, develop, and debug production software for P-states, DVFS, and power-management technologies across data-center GPUs.

The role spans hardware-software interfaces, kernel-level development, and collaboration with architecture, ASIC, and platform teams to ensure robust, efficient performance in AI workloads.

Qualifications

• BS or MS in Computer Science, Computer Engineering, Electrical Engineering, or related field, or equivalent experience.
• 2+ years of system software experience or strong project coursework.
• Strong C programming with kernel-space experience.
• Good understanding of OS fundamentals, arch, drivers, embedded/real-time software.

Responsibilities

• Design, build, and debug GPU power- and performance-management software focusing on P-states and DVFS.
• Develop control policies to optimize GPU performance, power, and thermals for data-center workloads.
• Support full product lifecycle from requirements to production support.
• Collaborate with GPU architects to define hardware-software interfaces for future processors.
• Analyze interactions among workloads, clocks, voltages, and system policies.
• Triaging and resolving power, performance, stability, and reliability issues across firmware and drivers.
• Assist validation strategies and automation for correctness and robustness.
• Write technical documentation and interface definitions for features.
• Partner with distributed teams across architecture, ASIC, firmware, and platform teams.

Skills

C programming

Kernel development

OS fundamentals

Device-driver architecture

Debugging across layers

Hardware programming

Education

BS/MS in CS/CE/EE

Job description

NVIDIA Corporation is seeking a System Software Engineer to join the GPU Performance and Power Management Software team in Santa Clara, CA. You will design, develop, and debug production software for P-states, DVFS, and power-management technologies across data-center GPUs.

The role spans hardware-software interfaces, kernel-level development, and collaboration with architecture, ASIC, and platform teams to ensure robust, efficient performance in AI workloads.