Join NVIDIA’s Applied Power Architecture team as a Senior Datacenter GPU Power Architect to lead the development of cutting-edge GPUs that drive AI, HPC, Automotive, GeForce, and Mobile products. Your role involves conceiving methodologies for power estimation models and tools, setting power targets, and conducting early architecture exploration with a focus on energy efficiency and TCO improvements at both GPU and datacenter levels. You will deploy machine learning techniques to create accurate performance and power models of GPUs, CPUs, switches, and platforms, while also performing pre-silicon thermal analysis for next-generation GPUs. This position requires expertise in low-power design techniques such as multi-VT, clock gating, and DVFS, along with a deep understanding of processors, servers, and system-SW architectures. Familiarity with Python, silicon data analysis, and performance monitors used in modern processor architectures is essential, alongside strong interpersonal skills to collaborate effectively across cross-functional teams including architects, designers, VLSI engineers, software developers, management, and marketing.
Skills
Python
GPU
HPC
AI
Machine Learning
Thermal Analysis
Chiplets
High Speed Interconnects
Power Estimation Models
Performance Monitors
VLSI
Dynamic Voltage-Frequency Scaling
Multi-VT
Clock Gating
Power Gating
Datacenter Scale Workloads
What you'll do
Conceive flows, methodologies, and KPIs for GPU products and systems like NVIDIA DGX/HGX datacenters.
Set power targets for future projects and track ASIC milestones to enable impactful product roadmap decisions.
Develop highly accurate power and performance models using machine learning techniques for GPUs, CPUs, and platforms.
Analyze workload characteristics for GenAI/HPC workloads at datacenter scale to drive new HW/SW features.
Conduct pre-silicon thermal analysis for next-gen GPUs including design of thermal usecases and driving mitigation features.
Model and analyze cutting-edge technologies like chiplets and high-speed/high-density interconnects.
What we're looking for
MSEE/MSCE or equivalent experience with a focus on power/performance optimization.
Over 5 years of experience in energy-efficient chip/system design and related trade-offs.
Proficiency in low-power design techniques including multi-VT, clock gating, and DVFS.
Deep understanding of GPU processors, servers, and system-SW architectures.
Experience with Python and silicon data analysis for performance modeling.
Familiarity with modern processor architecture performance monitors/simulators.
Strong interpersonal skills and ability to collaborate effectively across teams.
Market check
Salary context
This
$168,000–$264,500
range sits above
55%
of similar postings on FindRole.
Peer median band
$168,000–$250,700
Median floor and ceiling across peers.
Typical midpoint (25–75%)
$177,250–$235,750
Middle half of comparable postings.
Based on 240 comparable postings.*
* 240 is the maximum number of comparable postings sampled.
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
802 open roles
on FindRole.
Listed pay typically runs
$184,000–$287,500
across 798 roles with salary data.