Senior Datacenter GPU Power Architect

NVIDIA Ltd.
Santa Clara, CA, United States
6 days ago

Role details

Contract type
Permanent contract
Employment type
Full-time (> 32 hours)
Experience level
Expert
Experience required
8 years minimum
Working hours
Regular working hours

Tech stack

Artificial Intelligence Very-Large-Scale Integration Data Analysis Data Centers Microprocessors Python (Programming Language) Machine Learning Graphics Processing Unit (GPU) High Performance Computing Application Specific Integrated Circuits Perf (Linux)

Job description

Experteer Overview In this role you will lead the development of power and performance estimation models for GPU systems at scale, guiding the datacenter-focused product roadmap. You will explore energy-efficient architectures for GPUs and datacenters, set power targets for future projects, and apply machine learning to improve power/performance predictions. You’ll work with cross-functional teams to shape features that deliver Perf/Watt improvements for AI, HPC, and Datacenter workloads. This role offers an opportunity to influence pre-silicon thermal design and system-level power efficiency strategies with direct impact on product success. Compensation / Benefits * Conceive flows, methodologies, and KPIs for power estimation models/tools for GPU products and systems (e.g., DGX/HGX datacenters) * Explore energy-efficient GPU and datacenter architectures during early design phases * Set power targets for future projects and track ASIC milestones to drive Perf@Watt decisions * Deploy ML techniques to build accurate power and performance models for GPUs, CPUs, switches, and platforms * Understand workload characteristics for GenAI/HPC at datacenter scale to drive new HW/SW features for Perf@Watt gains * Perform pre-silicon thermal analysis, design thermal use cases, and drive thermal mitigation features * Model and analyze cutting-edge technologies like chiplets and high-density interconnects * Collaborate with Architects, Designers, VLSI, Software, Management and Marketing to influence the roadmap Tasks * MSEE/MSCE, PhD preferred, or equivalent experience in Power/Performance estimation and optimization * 8+ years of experience * Strong knowledge of energy-efficient chip/system design and related tradeoffs * Familiarity with low power techniques (multi-VT, clock gating, power gating, DVFS) * Deep understanding of processors/servers/system-SW architectures and their performance/power modeling * Familiarity with Python and silicon data analysis * Familiarity with performance monitors/simulators used in modern processor architectures * Strong interpersonal and organizational skills and team orientation Key requirements * equity * benefits * competitive compensation * global impact * growth opportunities * equity participation

Requirements

techniques to build accurate power and performance models for GPUs, CPUs, switches, and platforms * Understand workload characteristics for GenAI/HPC at datacenter scale to drive new HW/SW features for Perf@Watt gains * Perform pre-silicon thermal analysis, design thermal use cases, and drive thermal mitigation features * Model and analyze cutting-edge technologies like chiplets and high-density interconnects * Collaborate with Architects, Designers, VLSI, Software, Management and Marketing to influence the roadmap Tasks * MSEE/MSCE, PhD preferred, or equivalent experience in Power/Performance estimation and optimization * 8+ years of experience * Strong knowledge of energy-efficient chip/system design and related tradeoffs * Familiarity with low power techniques (multi-VT, clock gating, power gating, DVFS) * Deep understanding of processors/servers/system-SW architectures and their performance/power modeling * Familiarity with Python and silicon data analysis * Familiarity with aaaaaaaaa

  • monitors/simulators used in modern processor architectures * Strong interpersonal and organizational skills and team orientation Key requirements * equity * benefits * competitive compensation * global impact * growth opportunities * equity participation

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on us.experteer.com

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

51 sec

Repurposing hardware and operating underwater data centers

Chris Heilmann +1 · LIVE

52 sec

Running persistent Linux environments directly on Windows

Ben Breard Ben Breard · WWC 2025

1:48 min

Automating exploratory data analysis within training pipelines

Dora Petrella · WWC 2023

2:18 min

Replacing legacy CPUs to reduce data center energy consumption

Thomas Schmidt Thomas Schmidt · WWC 2024

4:03 min

Managing massive power consumption scaling in AI data centers

Stephan Gillich Stephan Gillich +3 · WWC 2024

2:08 min

History and scale of NVIDIA GPU computing

Paul Graham Paul Graham · LIVE

Videos

See all

Related articles

See all