Senior Silicon Power and Thermal Controllers Engineer

NVIDIA•Santa Clara, CA

8d•$168,000 - $310,500•Hybrid

About The Position

NVIDIA's Silicon Co-Design Group (SCG) is responsible for bringing every GPU, SoC, and CPU silicon program from initial power-on to high-volume production. SCG operates at the intersection of architecture, design, marketing, operations, and productization, developing innovative solutions for Datacenter, Server, Gaming, Robotics, Automotive, and Embedded markets. We are seeking a Senior Silicon Power and Thermal Controllers Engineer to design, implement, and productize the power-performance and thermal-control mechanisms integrated into every GPU, CPU, and SoC. This role bridges silicon, firmware, platform, and software, focusing on controllers that determine product performance within thermal and power constraints. The ideal candidate will leverage AI to optimize debug and modeling cycles, applying sound judgment to enhance efficiency and mitigate risks.

Requirements

BS or MS in Electrical Engineering, Computer Engineering, Systems Engineering, or related field (or equivalent experience).
6+ years implementing power and thermal controllers in firmware for GPU, CPU, or SoC products.
Hands-on experience with system-level silicon bring-up and validation, DVFS, power characterization and modeling, performance analysis, and perf-per-watt optimization.
Background in implementing system-level features, thermal policies, and data-analysis and statistics workflows.
Solid understanding of digital design, circuit analysis, CPU/GPU/SoC architecture, PTPX, advanced process technologies, and transistor/device physics.
Demonstrated experience operating across globally distributed and offshore engineering teams.
Strong written and verbal communication; able to translate complex post-silicon signals into crisp, decision-ready options for executive leadership.

Nice To Haves

Background in gaming, automotive, or datacenter market segments.
Track record of shipping system-level perf-per-watt or thermal-policy features that measurably improved a product at scale.
Proficiency with AI productivity tools (Claude, Copilot, ChatGPT, or equivalent) applied to power debug, modeling, or analysis workflows — and a clear view of the outcome and the guardrails you put in place.
Comfort navigating ambiguity, building technical structure inside fast-moving silicon programs, and working with global teams from diverse cultural backgrounds.

Responsibilities

Design, implement, and tune silicon power and thermal controllers in close partnership with firmware, hardware, software, and design/power-architecture teams, from specification through productization.
Drive debug and resolution of power-limiting constraints, delivering efficient, time-to-market product-specific customizations that unlock performance without compromising the thermal envelope.
Deliver system-level power optimizations across silicon, platform, software, and manufacturing for products ranging from large-scale datacenter accelerators to low-power client devices.
Partner with the SCG Tools team to advance modeling, analysis, and test infrastructure, refining methodologies, sharpening procedures, and integrating new closed-loop techniques into production.
Validate silicon power and thermal features across multi-functional teams from bring-up through production silicon, and be responsible for the WARs and productized fixes through to confirmation.
Translate complex power, thermal, and performance signals into decision-ready options for leadership regarding POR, binning, and program-impacting risks.
Collaborate with system architects, chip and board designers, software/firmware engineers, power-architecture engineers, Product Definition Engineers, and ATE engineers in a high-energy environment to bring industry-defining products to market.