NVIDIA designs the silicon behind AI, accelerated computing, and graphics. Power and thermal architecture decisions sit behind every watt of performance and every degree of thermal headroom! We are the Silicon Co-Design Group (SCG). We are hiring a Principal Architect to scout the research and industry landscape, identify emerging system-level co-design ideas in power and thermal, and drive them across teams into product differentiation across NVIDIA's roadmap. This role shapes system, platform, and datacenter feature/behavior, and partners with teams across Nvidia. SCG scope spans across architecture, design, software, operations, platforms, and productization.
What you'll be doing:- Architect next-generation system, platform, and datacenter-level power and thermal co-design solutions. Scan internal research, academia, standards bodies, and silicon, memory, packaging, and platform partners for what is emerging.
- Build the product differentiation case for each candidate idea, performance, power, reliability, schedule, cost, and brainstorm what is worth pursuing.
- Lead end-to-end co-design from concept to product. Drive alignment across architecture, VLSI, software, platform, packaging, and operations teams to land selected technologies in production.
- Shape innovation across workload-aware power and thermal controls, closed-loop platform telemetry, datacenter-class power compliance, platform-scale energy buffering, advanced cooling intercepts, and emerging memory co-design.
- Maintain a living intercept pipeline. Track candidates, productization status, decision gates, and product axes. Brief SCG and broader NVIDIA leadership on what is next.
- Collaborate with system architects, platform and software engineers, manufacturing partners, and external researchers to bring next-generation products to market.
What we need to see:- BS, MS, or PhD in Electrical Engineering, Computer Engineering, Computer Science, or equivalent experience.
- 15+ years in system-level power, thermal, or related architecture, with deep expertise in at least one of: system power management, system thermal architecture, platform energy architecture, workload-aware power and thermal controls, or memory co-design.
- External technical recognition, premier publications, patents, or industry standards contributions, and active contributions to standards bodies, consortia, or external technical communities.
- Track record of taking research-grade ideas through system co-design and into measurable product impact.
- Demonstrated multi-functional influence in aligning teams across the company without direct reporting authority.
- Excellent problem-solving, partnership, and social skills.
Ways to stand out from the crowd:- Curious about turning research into a production system co-design? Here is what makes a strong candidate.
- PhD or equivalent experience with sustained research contributions after entering industry.
- Machine learning or data-driven techniques applied to system power, thermal modeling, or design-space exploration.
- Background in system reliability and variability, managing aging based on usage patterns, RAS, lifecycle management, and the intersection with power and thermal.
- Hands-on familiarity with emerging memory technologies, including advanced HBM and stacked memory.
- Active contributions to standards bodies, consortia, or external technical communities.
As a member of the team, you will thrive on solving problems no one else can solve. Your decisions will not just shape a program, but also the technology's trajectory.
Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 232,000 USD - 368,000 USD.
You will also be eligible for equity and benefits.
Applications for this job will be accepted at least until June 29, 2026.
This posting is for an existing vacancy.
NVIDIA uses AI tools in its recruiting processes.
