GPU Energy Modeling Engineer (ML Power Models)

NVIDIA Corporation; Santa Clara (CA); On-site; USD 136,000 - 219,000; Full time

Benefits offered by this job

Equity compensation

Benefits

Job summary

NVIDIA Corporation in Santa Clara, California is seeking an Architecture Energy Modeling Engineer to join the Power Modeling, Methodology and Analysis Team. You will develop machine-learning powered energy models to study and reduce GPU power consumption and work with architects, designers, and performance engineers to improve perf/watt across NVIDIA’s GPUs and Tegra platforms.

The role involves prototyping energy models for new architectural features, training models with ML and statistics, and

Qualifications

• MS or PhD in Electrical/Computer Engineering, CS or equivalent experience.
• Strong coding skills in Python and C++.
• Background in ML, AI, or statistical modeling.
• Background in architecture and energy-efficient GPU design.
• Familiarity with Verilog and ASIC design is a plus.

Responsibilities

• Develop ML-based power models to analyze GPU energy consumption.
• Collaborate with Architects, ASIC, Low Power and Performance Engineers to study energy modeling.
• Develop and own methodologies to train models using ML or statistics.
• Improve model accuracy with different representations and learning algorithms.
• Integrate power/energy models into performance platforms for combined reporting.

Skills

Python

C++

Machine Learning

Computer Architecture

Verilog

Education

MS/PhD in Electrical Engineering / Computer Engineering / Computer Science

Tools

NVIDIA toolchains

Job description

NVIDIA Corporation in Santa Clara, California is seeking an Architecture Energy Modeling Engineer to join the Power Modeling, Methodology and Analysis Team. You will develop machine-learning powered energy models to study and reduce GPU power consumption and work with architects, designers, and performance engineers to improve perf/watt across NVIDIA’s GPUs and Tegra platforms.

The role involves prototyping energy models for new architectural features, training models with ML and statistics, and