Senior System Architect - LPU Platform Pathfinding

What You'll Do

• Lead pathfinding for system and rack architecture for new GPU/LPU platforms, building on existing NVIDIA architectures and improving them where it matters most.
• Tailor system-level solutions to improve performance, efficiency, and scalability for LPU-based systems and workloads.
• Define rack, node, and subsystem requirements across power, cooling, mechanics, SI/PI budgets, connectivity, management, and reliability.
• Collaborate with mechanical, electrical, SI/PI, networking, firmware, and data center operations teams to converge on practical architectures and execution plans.
• Drive SI/PI, power, and thermal feasibility through focused modeling, simulation, and experiments, then feed results back into designs.
• De-risk new architectures with targeted prototypes and experiments, and document clear specs, interfaces, and guidelines so teams can move fast.
• What we need to see: BS in Electrical Engineering, Mechanical Engineering, Computer Engineering, or related field (or equivalent experience); MS/PhD preferred. 8+ years in server, storage, networking, or rack-level hardware, including several years in system or platform architecture and pathfinding.
• Strong experience with mechanical aspects of data center hardware: rack structures, packaging, air or liquid cooling, cabling, and serviceability.
• Experience owning complex cross-functional decisions and enjoys working at rack scale.
• Strong background in electrical architecture and PDN: rack and board power trees, redundancy, protections, and high-speed interfaces/SI-PI fundamentals.
• Solid understanding of data center infrastructure: rack power distribution, network fabrics, structured cabling, grounding, safety, and regulations.
• Proven ability to lead cross-functional decisions, explain tradeoffs clearly, and deliver architectures under ambiguity and tight schedules.
• Ways to stand out from the crowd: Designed GPU, accelerator, or other high-power AI systems, including multi-GPU/LPU nodes and dense rack solutions.
• Defined rack-level networking architectures such as leaf/spine fabrics, TOR strategies, and structured cabling.
• Owned end-to-end SI/PI for complex platforms, from budgeting and simulations through lab correlation and signoff.
• Led platform bring-up and validation at scale, correlating architecture assumptions with measured behavior.
• Acted as a technical leader: mentoring engineers, scaling processes and tools for rack architecture, and contributing to standards, publications, or patents in server or rack design, SI/PI, power delivery, or thermal and mechanical design.
• At NVIDIA, we build systems that push the limits of what’s possible in AI, HPC, and accelerated computing.
• We’re excited to see how you will help design the next generation of platforms and how GPUs and LPUs come together at rack scale! With competitive salaries and a generous benefits package, we are widely considered to be one of the technology world’s most desirable employers.
• We have some of the most brilliant people in the world working for us and, due to unprecedented growth, our teams are rapidly growing.
• Are you passionate about becoming a part of a best-in-class team supporting the latest in GPU and AI technology? If so, we want to hear from you.
• Your base salary will be determined based on your location, experience, and the pay of employees in similar positions.
• The base salary range is 184,000 USD - 287,500 USD for Level 4, and 224,000 USD - 356,500 USD for Level 5.
• You will also be eligible for equity and benefits .
• Applications for this job will be accepted at least until April 18, 2026.
• This posting is for an existing vacancy.
• NVIDIA uses AI tools in its recruiting processes.
• As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.