This role pays less than
94%
of similar roles. Most pay
$187,850–$236,487
— the shaded band above.
At the midpoint, this role pays about
$160k
versus about
$212k
for comparable roles.
Based on 240 similar postings.
Employer
About Nvidia
Nvidia is a leading designer of graphics processing units (GPUs) and system-on-chip units, powering gaming, professional visualization, data centers, and artificial intelligence workloads. Industry: Semiconductors & AI Computing
Nvidia currently has
1150 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 912 roles with salary data.
System Software Engineer - GPU Power and Performance Management will join the GPU Performance and Power Management Software team to design, develop, and debug production software for performance states and Power Management Controllers. The role involves developing control policies and software mechanisms to optimize GPU performance, power, thermals, and energy efficiency under demanding data-center workloads. You will support features through the full product lifecycle, including pre-silicon development, silicon bring-up, and production support while collaborating with architects to define hardware-software interfaces. Key responsibilities include investigating issues across firmware, drivers, and platform software. Required skills include proficiency in C for low-level kernel software, a deep understanding of operating system fundamentals, computer architecture, device-driver architecture, and concurrency. The work focuses on the intersection of hardware architecture, embedded firmware, and AI workloads to solve complex power management challenges for next-generation data-center GPUs.
Design, build, and debug GPU power and performance management software including P-state management and DVFS.
Develop control policies to optimize GPU performance, power, thermals, and energy efficiency for data-center workloads.
Support the full product lifecycle from requirements and architecture through pre-silicon validation and silicon bring-up.
Define and implement hardware-software interfaces in collaboration with GPU architects and hardware designers.
Analyze complex interactions between workloads, clocks, voltages, power limits, thermals, and system-level policies.
Investigate and resolve power, performance, stability, and reliability issues across firmware, drivers, and platform software.
Execute validation strategies and automation for functional correctness, transition latency, and performance-per-watt metrics.
Create technical documentation and interface definitions for new features and hardware-software interactions.
What we're looking for
BS or MS degree in Computer Science, Computer Engineering, Electrical Engineering, or a related field, or equivalent experience.
2+ years of relevant industry experience, or strong coursework, internship, co-op, or project experience in system software.
Strong programming skills in C to develop, debug, and maintain low-level kernel software.
Understanding of operating-system fundamentals, computer architecture, device-driver architecture, embedded/real-time software, concurrency, interrupt handling, and hardware programming.
Ability to independently debug and analyze across multiple layers of software and hardware while reading hardware specifications and interface definitions.
Strong problem-solving skills and excellent written and verbal communication skills.
Experience with GPU, CPU, accelerator, or SoC power and performance management (preferred).
Exposure to P-states, DVFS, clock/voltage control, thermal management, or workload-aware system behavior (preferred).
CUDA
C++
C
GPU
Kernel Software
performance-engineering
Computer Architecture
Operating Systems
Concurrency
Memory Management
Python
HPC
Deep Learning
Profiling
Firmware
Hardware/Software Co-design
Pre-silicon Analysis
C
C++
Python
Firmware
Kernel Drivers
ARM
Power Management
DVFS
Computer Architecture
Operating Systems
Data Center
Simulation
Emulation
Memory-Mapped IO
Interrupts