AI GPU Power Architect - Craft Ultra-Efficient AI Chips

NVIDIA Gruppe; Santa Clara (CA); On-site; USD 100,000 - 190,000; Full time

Job summary

NVIDIA is seeking a New College Grad to contribute to power estimation models and tools for GPUs and DGX systems. The role emphasizes energy efficiency and Datacenter scale performance vs.

power analysis, using ML to develop accurate power and performance models for GPUs, CPUs, and interconnects. You will explore GPU/system architectures and workload characteristics for GenAI/HPC at Datacenter scale, driving HW/SW features for Perf@Watt improvements.

Qualifications

• Pursuing or recently completed a Bachelor's or Master's in Electrical Engineering, Computer Engineering, or equivalent experience.
• Strong understanding of Computer Architecture and Digital Logic Design/VLSI Design.
• Proficiency with Python and data analysis packages like Pandas, NumPy, PyTorch.

Responsibilities

• You will be contributing to power estimation models and tools for GPU products and systems like NVIDIA DGX.
• Early GPU & System Architecture exploration with focus on energy efficiency and TCO improvements at GPU and Datacenter level.
• You will help with Performance vs Power Analysis for NVIDIA future product lineup.
• Deploy machine learning techniques to develop highly accurate power and performance models of our GPUs, CPUs, Switches, and platforms.
• Understand the workload characteristics for GenAI/HPC workloads at Datacenter Scale to drive new HW/SW features for Perf@Watt improvements.
• Modeling & analysis of cutting-edge technologies like high speed & high-density interconnects.

Skills

Computer Architecture & Digital Logic

Energy efficiency

Education

Bachelor's or Master's in Electrical Engineering or Computer Engineering

Tools

Python

Pandas

NumPy

PyTorch

Job description

NVIDIA is seeking a New College Grad to contribute to power estimation models and tools for GPUs and DGX systems. The role emphasizes energy efficiency and Datacenter scale performance vs.

power analysis, using ML to develop accurate power and performance models for GPUs, CPUs, and interconnects. You will explore GPU/system architectures and workload characteristics for GenAI/HPC at Datacenter scale, driving HW/SW features for Perf@Watt improvements.