Senior GPU Power & Performance Software Architect

NVIDIA Corporation; Santa Clara (CA); On-site; USD 224,000 - 431,000; Full time

Benefits offered by this job

Equity

Benefits package

Job summary

NVIDIA Corporation seeks a Senior System Software Engineer to join the GPU Performance and Power Management Software team. You will architect and implement power- and performance-management software for P-states and DVFS across data-center GPUs, interfacing hardware, firmware, drivers, OS, and AI workloads.

Lead design from requirements through silicon bring-up and production deployment, collaborating with architects and hardware teams to define interfaces and analyze telemetry and power

Qualifications

• BS or MS degree in CS/CE/EE or equivalent.
• 12+ years of experience crafting system software, embedded firmware, device drivers, or related production software.
• Strong C programming skills, debugging low-level software.
• Deep OS fundamentals, drivers, real-time software, concurrency, interrupts.
• Experience interpreting hardware specs and software interfaces for registers/telemetry.
• Strong hardware-software understanding and system-level perspective.
• Excellent written and verbal communication across teams.

Responsibilities

• Architect, build, and debug GPU power- and performance-management software.
• Develop real-time controllers and DVFS policies for performance, power, and thermals.
• Lead product lifecycle from requirements to production support.
• Collaborate with GPU architects to define interfaces for power-management.
• Analyze interactions among workloads, clocks, voltages, telemetry, and policies.
• Lead investigations of power, performance, stability, and reliability issues.
• Develop validation strategies and automation for correctness and latency.

Skills

C programming

Operating systems fundamentals

Device drivers

Debugging complex systems

Communication skills

Education

BS/MS in CS/CE/EE or equivalent

Job description

NVIDIA Corporation seeks a Senior System Software Engineer to join the GPU Performance and Power Management Software team. You will architect and implement power- and performance-management software for P-states and DVFS across data-center GPUs, interfacing hardware, firmware, drivers, OS, and AI workloads.

Lead design from requirements through silicon bring-up and production deployment, collaborating with architects and hardware teams to define interfaces and analyze telemetry and power