Power Architect - New College Grad 2026

NVIDIA NVIDIA · Semiconductors · Santa Clara, CA +1

This role focuses on architecting GPU power features and system-level power management solutions, including researching and developing solutions for energy efficiency problems in various GPU use cases. It also involves deploying machine learning techniques to create accurate power and performance models for GPUs and platforms.

What you'd actually do

  1. You will be working on architecting GPU power features and system level power management solutions for NVIDIA products.
  2. Collaborate closely with other Architects, Software Engineers, ASIC Design Engineers, and Product teams to study, devise and implement the power management strategy for NVIDIA's GPU roadmap.
  3. Research and develop solutions to address complex energy efficiency problems for various GPU use-cases such as: Deep Learning training, ADAS, Gaming, Video Playback, and Idle.
  4. Deploy machine learning techniques to develop highly accurate power and performance models of our GPUs and platforms.

Skills

Required

  • Pursuing or recently completed a MS or PhD in Electrical or Computer Engineering (or equivalent experience)

Nice to have

  • Knowledge of performance simulators/monitors and Low Power architectures/techniques
  • Working knowledge of Python, and frameworks/packages like: TensorFlow, Pandas, NumPy, PyTorch
  • Exposure to tools/flows such as Design Compiler, PTPX, and Power Artist
  • Experience with lab setup and measurement using equipment such as scope/DAQ
  • A master’s degree/internship with a focus/projects in Low Power Architecture, power modeling, and deep learning

Other signals

  • Deploy machine learning techniques to develop highly accurate power and performance models of our GPUs and platforms.