Principal System Architect, GPU

Job Title

Principal System Architect, GPU

Role Summary

Principal System Architect responsible for defining and driving the architecture of complex, high-volume GPU System-on-Chip (SoC) platforms. The role is hands-on and cross-functional, working with RTL, verification, physical design, firmware, and software teams to deliver scalable, high-performance products.

Main mission: set SoC-level architecture, perform trade-off analysis, and lead technical direction and mentorship across multiple engineering teams to achieve performance, power, and scalability targets.

Experience Level

Senior — typically requires over 15 years of experience in SoC architecture development or similar technical leadership roles.

Responsibilities

Core responsibilities include architectural definition, evaluation, and cross-team leadership.

• Define and drive architecture for high-volume GPU products to meet performance and scalability goals.
• Perform and guide power and performance evaluation, trade-off assessments, and architectural modeling for chip, package, and system design.
• Lead improvements in architecture, methodology, and tools to improve design scalability.
• Specify and optimize SoC subsystems including memory architecture, test infrastructure, and power management.
• Collaborate with RTL, verification, physical design, firmware, and software teams to implement and integrate system components.
• Produce clear technical documentation of SoC architecture, specifications, and development trade-offs.
• Provide technical leadership and mentor junior architects and engineers.

Requirements

Must-have technical skills and experience; nice-to-have items listed separately.

• 15+ years experience in SoC architecture development or equivalent technical leadership.
• Proven track record of defining and delivering multiple high-volume SoC systems (CPU, GPU, modem, networking, or similar).
• Proficiency in evaluating power/performance and architectural modeling using high-level programming or modeling languages.
• Strong understanding of SoC fundamentals: memory hierarchy, coherency, clocking, power domains, boot/reset, test, and debug methodologies.
• Hands-on experience with silicon bring-up, debug, and performance/power tuning.
• Excellent interpersonal, leadership, written, and verbal communication skills; ability to influence across organizations.

Nice-to-have:

• Experience with GPU or AI accelerator architecture, multi-GPU systems, and off-chip I/O technologies.
• Knowledge of modern packaging technologies and their trade-offs.
• Familiarity with AI workload characteristics and optimization.
• Strong analytical skills focused on optimizing performance, power, area, and complexity.

Education Requirements

Master's degree (or equivalent experience) in Computer Science, Electrical Engineering, Computer Engineering, or a closely related technical field. Equivalent practical experience accepted.

About the Company

Company: NVIDIA

Headquarters: Santa Clara, California, USA

NVIDIA is a global leader in accelerated computing, renowned for its innovative solutions in AI and digital twins that transform diverse industries. The company specializes in networking technologies, providing end-to-end InfiniBand and Ethernet solutions for servers and storage that optimize performance and scalability. NVIDIA serves sectors such as high-performance computing, enterprise data centers, and cloud computing, constantly reinventing its products and services to stay ahead in the market.