Power Modeling Engineer for AI Workloads

NVIDIA Corporation; Austin (TX); On-site; USD 136,000 - 265,000; Full time

Benefits offered by this job

Equity

Benefits

Job summary

NVIDIA Corporation is seeking an Architect Energy Modeling Team member to collaborate with ASIC and software teams to study and implement energy modeling techniques for GPUs, CPUs, and Tegra SOCs. You will develop tools to generate, sanitize, and integrate data into power models, enabling better energy efficiency across NVIDIA’s next generation chips.

The role requires MS/PhD with 5+ years’ experience, strong Python and C++, and a background in VLSI and computer architecture.

Qualifications

• MS (or equivalent experience) with 5+ years of experience in related fields.
• Strong coding skills, preferably in Python and C++.
• Background in VLSI, digital design, and computer architecture concepts.
• Basic understanding of power and energy estimation and low power design.
• Experience with ML/AI and statistical modeling is a plus.

Responsibilities

• Define and implement tools and methodologies for energy modeling data generation from post-layout netlists.
• Develop tools to sanitize metrics for high correlation accuracy.
• Integrate power models with performance tools and improve data flows.
• Identify runtime/memory bottlenecks to speed up model delivery.
• Mine data from pre/post-silicon performance runs to find key data paths and bottlenecks.
• Provide feedback to design teams to improve energy efficiency.
• Collaborate with floorplanning, verification, and emulation teams to integrate data movement models.
• Explore ML techniques to answer design questions and set power targets.
• Ensure easy storage/retrieval of data and visualisation via platforms like PowerBI/OpenSearch.

Skills

Python

C++

Algorithms analysis

VLSI

Digital design

Computer architecture

Machine learning

Education

MS or PhD in related field

Tools

PowerBI

OpenSearch

Job description

NVIDIA Corporation is seeking an Architect Energy Modeling Team member to collaborate with ASIC and software teams to study and implement energy modeling techniques for GPUs, CPUs, and Tegra SOCs. You will develop tools to generate, sanitize, and integrate data into power models, enabling better energy efficiency across NVIDIA’s next generation chips.

The role requires MS/PhD with 5+ years’ experience, strong Python and C++, and a background in VLSI and computer architecture.