Senior GPU Memory System Architect

Details

NVIDIA is seeking a motivated architect to work with a team solving complex problems while optimizing performance, area, complexity, and power on leading-edge silicon processes. The GPU memory architecture team creates innovative products for data centers, autonomous vehicles, AI, gaming, and mobile systems.

Responsibilities

• Develop architecture and microarchitecture for GPU memory systems, memory management, virtualization, and security, optimizing performance, power efficiency, complexity, area, effort, and schedule.
• Participate in performance simulation of features that improve translation efficiency for memory and I/O access using protocols such as PCIe.
• Implement and maintain high-level functional and performance models.
• Analyze benchmarks, application workloads, and performance simulation results to identify microarchitecture optimization opportunities.
• Define and perform experiments to study system behavior, present results to the broader team, and propose improvement mechanisms.
• Create architectural specifications and customer-facing documents.
• Work with industry partners to generate specifications that consider software interfaces to the GPU.
• Debug performance and functional issues using high-level models, RTL simulation, silicon, and systems.

Requirements

• Master's degree or equivalent experience in Electrical Engineering, Computer Science, Computer Engineering, or a related field.
• A PhD focused on computer architecture is a plus.
• Three or more years of meaningful experience in GPU or CPU architecture and development, particularly in interconnects, QoS, memory hierarchy, memory models and ordering, multifunction hardware accelerators, software, virtualization, and security.
• Strong communication and interpersonal skills.
• Ability to work in a dynamic, product-oriented, distributed team.
• Experience mentoring junior engineers and interns is a plus.

Preferred Qualifications

• Experience with hardware memory management units, prefetching, accelerator IPs, and memory subsystem hierarchies.
• Practical experience with multicore systems, coherent interconnects, and industry I/O protocols such as PCIe and CXL.
• Experience with encryption, compression, confidential computing, virtualization, or security.

Benefits

• Competitive salary.
• Equity and benefits.
• NVIDIA is an equal opportunity employer committed to fostering a diverse work environment.

The base salary range is USD 152,000–241,500 for Level 3 and USD 184,000–287,500 for Level 4. The base salary is determined based on location, experience, and the pay of employees in similar positions. Applications will be accepted at least until March 21, 2026. This posting is for an existing vacancy. NVIDIA uses AI tools in its recruiting processes.