Senior GPU System Architect

Job Title

Senior GPU System Architect

Role Summary

Design and architect multi-GPU scale-up and scale-out systems for next-generation datacenter platforms focused on AI and HPC. The role defines system topologies, interconnect and memory integration, and hardware-software co-design to deliver scalable, high-performance GPU platforms.

The position works across ASIC, packaging, board, and software teams to evaluate system trade-offs, perform modeling and simulation, and deliver resilient rack- and node-scale GPU systems.

Experience Level

Senior — typically 8 or more years of relevant experience in system design, ASIC/SoC architecture, or related engineering roles.

Responsibilities

Primary responsibilities include architecting multi-GPU systems, evaluating interconnects and memory interactions, and enabling hardware-software co-design across compute and communication layers.

• Architect multi-GPU topologies for scale-up and scale-out configurations balancing throughput, scalability, and resilience.
• Define and evaluate architectures for high-speed interconnects (e.g., NVLink, Ethernet) co-designed with GPU memory systems.
• Collaborate to architect RDMA-capable hardware and transport-layer optimizations for large-scale GPU deployments.
• Develop and modify system models, run simulations, and perform bottleneck analyses to guide design trade-offs.
• Work with GPU ASIC, compiler, library, and software teams to enable efficient hardware-software co-design across compute, memory, and communication layers.
• Contribute to interposer, package, PCB, and switch co-design for high-density multi-die, multi-package, rack-scale systems.

Requirements

Must-have technical skills and experience for successful performance in this role.

• 8+ years of relevant experience in system design and/or ASIC/SoC architecture for GPU, CPU, or networking products.
• Deep understanding of communication interconnect protocols such as NVLink, Ethernet, InfiniBand, CXL, and PCIe.
• Experience with RDMA/RoCE or InfiniBand transport offload architectures.
• Proven ability to design multi-GPU/multi-CPU topologies with awareness of bandwidth scaling, NUMA, memory models, coherency, and resilience.
• Experience with hardware-software interaction, drivers, runtimes, and performance tuning for distributed computing systems.
• Strong analytical and system-modeling skills (Python, SystemC, or similar).
• Excellent cross-functional collaboration skills with silicon, packaging, board, and software teams.

Nice-to-have:

• Background in AI and HPC system design.
• Experience with NICs, DPU architecture, or other transport offload engines.
• Expertise in chiplet interconnects, multi-node fabrics, or interposer/2.5D/3D package co-design.

Education Requirements

BS, MS, or PhD in Electrical Engineering, Computer Engineering, or a related technical field — or equivalent practical experience.

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.