Senior Silicon Product Architect, Performance and Power

Job description

NVIDIA has been redefining accelerated computing, computer graphics, and artificial intelligence through groundbreaking technology and exceptional people. We are seeking a Senior Silicon Product Architect to define the technical strategy for next-generation products by connecting silicon capabilities, customer workloads, and system-level opportunities! As part of Silicon CoDesign, you’ll connect silicon capabilities with customer workloads, develop innovative features and system-level solutions, and guide product strategy. You’ll own the Product Soul, advise engineering teams, and mentor engineers across the computing stack What you’ll be doing: Product vision: Own the Product Soul, turning customer needs and workloads into clear performance, power, and efficiency goals, priorities, and tradeoffs. Performance and power co-design: Architect next-generation performance and power management features and system-level solutions, partnering across teams from concept through silicon to shipping products. Competitive edge: Benchmark competing architectures and prioritize investments that improve performance, power efficiency, product differentiation, and customer value. Product decisions: Define operating points, configurations, and binning strategies with engineering teams; validate models against silicon data and flag gaps and risks early. Team impact: Mentor engineers, lead technical reviews, and set a high standard for data analysis, technical reasoning, and clear communication. What we need to see: MS or PhD in EE, CE, CS, systems engineering, or equivalent experience. 12+ years in silicon or system performance and power, with ownership of product architecture or technical strategy. Strong judgment in turning customer and business needs into measurable product goals and architectural decisions. Deep silicon performance and power expertise, including device behavior, voltage-frequency characteristics, process variation, power management, and electrical and thermal limits. Broad CPU, GPU, or SoC architecture knowledge, including memory, interconnects, and hardware/software co-design. Experience with first-principles modeling, workload analysis, competitive benchmarking, statistics, and data analysis. Strong technical writing, presentation, and mentoring skills, with experience influencing decisions across global and offshore teams. Ways to stand out from the crowd: Understanding of LLM architectures and training or inference workloads. Experience with rack or datacenter performance and power, or across client, embedded, automotive, and networking products. Hands-on experience with silicon bring-up, performance and power characterization, operating points, or binning. A record of proposing novel system-level concepts or features with measurable product value. Join NVIDIA to help solve some of computing’s most challenging problems. #LI-Hybrid You will also be eligible for equity and benefits. Applications for this job will be accepted at least until November 3, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes. NVIDIA is committed to fostering an inclusive work environment and proud to be an equal opportunity employer. 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.