Join NVIDIA, a pioneer in GPU technology and a driving force behind AI innovation. We are seeking experienced Memory Subsystem Architects with exceptional analytical and system architecture skills. This role involves contributing to the advancement of GPU architecture and simulators, analyzing performance issues, and optimizing memory system efficiency.

As part of a dynamic, product-oriented team, you will engage in performance modeling, simulation, and debugging of complex memory subsystems. Your work will be crucial in identifying and resolving performance bottlenecks within our cutting-edge GPU hardware and simulators.

Advance GPU Architecture and Simulators through contributions to testing infrastructure, metrics, and compilers.

Conduct performance modeling and simulation to enhance memory system efficiency.

Develop comprehensive test plans and build robust testing infrastructure.

Debug tests effectively on architecture simulators.

Perform in-depth performance and bottleneck analysis of sophisticated memory subsystem units and features.

Work with hardware models at various abstraction levels, including performance and RTL models, and emulators to identify system performance bottlenecks.

Collaborate closely with cross-functional teams, including ASIC design and verification.

Possess a Master's or Bachelor's degree in Electrical Engineering, Computer Science, Computer Engineering, or a related field, or equivalent practical experience.

Demonstrate at least 3 years of experience in system-level architecture and performance analysis.

Exhibit strong programming proficiency in C and C++, with exposure to Verilog/System Verilog being a significant advantage.

Show a solid understanding of memory subsystem architecture, including caches, MMU, memory controllers, NOC/interconnects, and computer architecture fundamentals.

Possess strong debugging and analysis skills, with experience using RTL dumps for failure analysis.

Familiarity with performance simulators, cycle-accurate/approximate models, or emulators for pre-silicon performance analysis is beneficial.

Excellent communication and interpersonal skills are essential for effective collaboration within a distributed, product-focused team.