SeniorPowerAnalysisandOptimizationEngineer

We’re looking for a Senior Power Architecture & Optimization Engineer to push the limits of energy efficiency using advanced analytics and AI, including LLMs trained specifically for power analysis. NVIDIA’s leadership in accelerated computing depends on building the most energy‑efficient GPUs and SoCs in the industry. As AI and graphics workloads scale explosively, we believe that Power Analysis and Optimization driven by AI and LLMs is the future—and a key differentiator for our next generations of GPUs and Tegra SoCs. In this role, you’ll be at the center of that effort—combining power architecture expertise with machine learning, reinforcement learning, data analytics, and large language models (LLMs) to invent new ways to model, analyze, and optimize energy consumption across full‑chip and unit‑level designs. **What You’ll Be Doing:** * Analyze full‑chip and unit‑level power using internal and industry‑standard RTL and gate‑level power tools, and translate data into concrete design and architectural improvements. * Develop and productionize power‑aware models and flows, including ML/RL‑based techniques for anomaly detection, dynamic power management, and design‑space exploration. * Design and train new LLMs that “learn the art” of power analysis from design data, power reports, bug histories, and best practices—so they can: * Assist engineers in interpreting complex power data * Propose likely root causes and candidate fixes * Recommend architectural and micro‑architectural optimizations for power * Perform comparative power analysis across workloads, products, and design options to identify trends, anomalies, and optimization opportunities that aren’t obvious from first principles alone. * Partner closely with Architects, Performance, Software, ASIC Design, and Physical Design teams to interpret power data, root‑cause power bugs, and drive fixes and design changes. * Prototype and evaluate new architectural features in Verilog, with a strong focus on their pow