JobsSenior Compute Kernel Architect, GPU Power
NVIDIA logo

Senior Compute Kernel Architect, GPU Power

NVIDIA

Location

Santa Clara, CA

Type

Full-time

Posted

6/30/2026

Compensation

$184,000 - $356,500 per year

Master's with 5+ Years of Experience
PhD with 5+ Years of Experience
Approval 99.2%·Filings 1,781·New hires 873·
👑 Elite Sponsor
·FY 2025

Job description

NVIDIA is looking for a Compute Kernel Performance Architect who specializes in writing, profiling, and analyzing CUDA kernels with a focus on power consumption and current draw. This role involves collaborating with hardware architects to validate power integrity and ensuring that chips can withstand real-world power scenarios. The position offers an opportunity to influence the GPU power architecture of future NVIDIA products, working at the intersection of GPU architecture, software, and silicon. The team collaborates closely with various departments to align methodologies from pre-silicon simulation through post-silicon bringup.

Requirements

  • MS or PhD in Computer Science, Electrical Engineering, or Computer Engineering or equivalent experience
  • 5+ years of experience in GPU kernel development, CUDA programming, or high-performance computing
  • Strong CUDA and C++ programming skills with hands-on experience writing and optimizing kernels at the assembly or PTX level
  • Experience with GPU performance profiling tools such as Nsight Compute, Nsight Systems, or nvprof
  • Solid understanding of GPU architecture including SMs, memory hierarchy, and power states
  • Working knowledge of Power Delivery Networks (PDNs) including board-level design and decoupling capacitors
  • Conceptual understanding of di/dt and its impact on voltage transients
  • Strong programming skills in Python for scripting and data analysis
  • Excellent communication skills and ability to work across hardware and software disciplines

Responsibilities

  • Design and develop CUDA kernels to enhance GPU power consumption targeting worst-case current draw
  • Collaborate with hardware power architects to validate PDN assumptions and di/dt specifications
  • Build and maintain a library of power stress microbenchmarks to stress PDN resonance and droop conditions
  • Analyze trade-offs between kernel throughput, power efficiency, and voltage stability
  • Partner with GPU architects, power circuit designers, and silicon validation engineers to align power stress methodologies

Benefits

  • Employees at NVIDIA are often offered comprehensive, day-one benefits—including medical, dental, and vision coverage with HSA support, life and disability insurance, an Employee Assistance Program, and a 401(k) with auto-enrollment. Many roles also have generous time off and holidays, donation matching (up to $10,000), and a wide menu of extras like FSAs, commuter benefits, legal and identity-theft protection, pet insurance, and wellness discounts. Optional programs can include student-loan and home-purchase support, plus family care resources and expert medical services.

Is this posting expired or inaccurate?