Senior Datacenter GPU Power Architect
NVIDIA · California, United States
- Hybrid
- Full-time
- $264,500 / year
- California, United States
Job highlights
- Design power estimation models for GPUs and datacenters.
- Explore architecture for energy efficiency and TCO.
- Set power targets and drive performance analysis.
- Develop ML models for power and performance.
- Collaborate with cross-functional teams on roadmap.
About the role
About the Role
NVIDIA is a world leader in providing energy-efficient, high-performance products, with a continuous investment in the research and development of hyper-efficient GPU and SOC architectures. We are constantly innovating to improve our ability to deliver exceptional Perf/Watt solutions across various sectors and verticals. Join NVIDIAs Applied Power Architecture team to develop state-of-the-art GPUs powering AI, HPC, Automotive, GeForce, and Mobile products.What You'll Be Doing
- Conceive flows, methodologies, and KPIs, and build power estimation models/tools for GPU products and systems like NVIDIA DGX/HGX based datacenters.
- Engage in early GPU & System Architecture exploration focusing on energy efficiency and Total Cost of Ownership (TCO) improvements at GPU and Datacenter levels.
- Set power targets for future projects, track ASIC milestones, and drive Performance vs. Power Analysis to inform impactful product roadmap decisions.
- Deploy machine learning techniques to develop highly accurate power and performance models for GPUs, CPUs, Switches, and platforms.
- Understand workload characteristics for GenAI/HPC workloads at Datacenter Scale to drive new HW/SW features for Perf@Watt improvements.
- Conduct pre-silicon thermal analysis for next-gen GPUs, including designing thermal use cases, power maps for thermal simulations, and driving thermal mitigation architectural features.
- Model and analyze cutting-edge technologies such as chiplets and high-speed, high-density interconnects.
- Collaborate with cross-functional teams, including Architects, Designers, VLSI, Software, Management, and Marketing, to influence the product roadmap.
What We Need To See
- MSEE/MSCE, preferably PhD, or equivalent experience in Power / Performance estimation and optimization techniques.
- 5+ years of experience.
- Strong knowledge of energy-efficient chip/system design fundamentals and related tradeoffs.
- Familiarity with low-power design techniques such as multi-VT, Clock gating, Power gating, and Dynamic Voltage-Frequency Scaling (DVFS).
- Deeper understanding of processors (GPU is a plus), servers, and system-SW architectures, and their performance/power modeling techniques.
- Familiarity with Python and Silicon data analysis.
- Familiarity with performance monitors/simulators used in modern processor architectures.
- Strong interpersonal and organizational skills, with the ability and desire to work as a great teammate.
About NVIDIA
NVIDIA is widely considered one of the technology world’s most desirable employers. Our products are leading the way with groundbreaking developments in Artificial Intelligence, High-Performance Computing, and Visualization. We have some of the most forward-thinking and hardworking people in the world working for us. If you love the challenge of crafting the fastest and most power-efficient chips in their class, we want to hear from you!Compensation and Benefits
Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is $168,000 - $264,500 USD for Level 4, and $196,000 - $310,500 USD for Level 5. You will also be eligible for equity and benefits.Equal Opportunity
NVIDIA is committed to fostering a diverse work environment and is proud to be an equal opportunity employer. We highly value diversity in our current and future employees and do not discriminate based on race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status, or any other characteristic protected by law. Key skills/competency:- GPU Architecture
- Power Estimation
- Performance Analysis
- Datacenter Systems
- Machine Learning
- Thermal Analysis
- Low Power Design
- Python
- Chip System Design
- HPC Workloads
Skills & topics
- GPU Architect
- Power Architect
- Datacenter
- NVIDIA
- GPU
- Power Estimation
- Performance Analysis
- AI
- HPC
- System Design
- Low Power Design
- Python
- Thermal Analysis
- Chip Design
- Senior Engineer
How to get hired
- Tailor your resume: Highlight your experience in GPU power architecture, estimation, and optimization techniques.
- Showcase your skills: Emphasize your knowledge of low-power design, system architectures, and Python proficiency.
- Demonstrate teamwork: Provide examples of successful collaboration with cross-functional teams.
- Prepare for technical questions: Be ready to discuss your experience with performance monitors, simulators, and thermal analysis.
- Research NVIDIA: Understand their commitment to AI, HPC, and energy efficiency.
Technical preparation
Master GPU architecture concepts.,Practice Python for data analysis.,Study low-power design techniques.,Review datacenter system architectures.
Behavioral questions
Describe a complex power optimization challenge.,How do you collaborate with cross-functional teams?,Share an experience driving product roadmap decisions.,How do you approach analyzing new technologies?
Frequently asked questions
- What is the application deadline for the Senior Datacenter GPU Power Architect role at NVIDIA?
- Applications for this Senior Datacenter GPU Power Architect position at NVIDIA will be accepted until at least January 18, 2026. It's advisable to apply well before this date to ensure your application is considered.
- What are the salary ranges for the Senior Datacenter GPU Power Architect position at NVIDIA?
- The base salary for the Senior Datacenter GPU Power Architect role at NVIDIA ranges from $168,000 - $264,500 USD for Level 4, and $196,000 - $310,500 USD for Level 5. Actual salary will depend on location, experience, and similar roles within the company.
- Does NVIDIA use AI in its recruitment process for the Senior Datacenter GPU Power Architect role?
- Yes, NVIDIA utilizes AI tools in its recruiting processes, including for roles like the Senior Datacenter GPU Power Architect. This can help streamline the evaluation of applications and identify suitable candidates.
- What level of education is preferred for the Senior Datacenter GPU Power Architect position at NVIDIA?
- NVIDIA prefers candidates with an MSEE/MSCE, and ideally a PhD, or equivalent experience in Power/Performance estimation and optimization techniques for the Senior Datacenter GPU Power Architect role.
- What kind of projects will a Senior Datacenter GPU Power Architect work on at NVIDIA?
- A Senior Datacenter GPU Power Architect at NVIDIA will work on conceiving power estimation models for GPUs and datacenters, exploring energy efficiency for AI/HPC, setting power targets, and analyzing cutting-edge technologies like chiplets.
- What are the key technical skills required for the Senior Datacenter GPU Power Architect role?
- Key technical skills for this role include strong knowledge of energy-efficient chip/system design, low-power techniques (DVFS, gating), processor/server architectures, Python, and performance simulation tools.
- What is the expected experience level for the Senior Datacenter GPU Power Architect at NVIDIA?
- NVIDIA is looking for candidates with at least 5 years of experience for the Senior Datacenter GPU Power Architect position, with a strong background in power and performance estimation and optimization.
- How does NVIDIA ensure diversity in its hiring for roles like the Senior Datacenter GPU Power Architect?