Architect - Performance Verification and Analysis

Job Title

Architect - Performance Verification and Analysis

Role Summary

Perform system- and application-level performance analysis for high-performance GPUs and SoCs. Use and develop hardware models, simulators, RTL testbenches and emulators to locate bottlenecks and drive architecture trade-offs.

Contribute analyses and infrastructure that improve performance, area, and power for AI, graphics, and HPC products.

Experience Level

Senior role. Posting requests 2+ years of relevant experience in system-level architecture and performance;

Responsibilities

Primary responsibilities include performance analysis, model and test development, and cross-team collaboration.

• Analyze performance and identify bottlenecks across complex GPUs and SoCs.
• Develop and use hardware models at multiple abstraction levels: performance models, RTL testbenches, and emulators.
• Work with architecture and design teams to evaluate performance, area, and power trade-offs.
• Develop workloads and test suites for graphics, machine learning, automotive, video, and computer vision applications.
• Drive methodologies to reduce turnaround time and find representative datasets for early performance analysis.
• Build infrastructure such as performance simulators, testbench components, and analysis tools.

Requirements

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

• 2+ years of relevant experience in system-level architecture and performance analysis.
• Strong understanding of SoC architecture, graphics pipeline, CPU architecture, memory subsystems, and NoC/interconnects.
• Proficient in C/C++ and scripting (Bash, Perl, or Python).
• Strong debugging and data/statistical analysis skills, including use of RTL dumps for debugging.
• Excellent communication and organization skills; ability to work in global teams.

Nice-to-have

• Experience with Verilog/SystemVerilog or SystemC/TLM.
• Exposure to performance simulators, cycle-accurate or approximate models, or emulators for pre-silicon analysis.
• Familiarity with GPU APIs (CUDA, OpenGL, DirectX) and advanced data analysis/visualization skills.

Education Requirements

BE/BTech or MS/MTech in a relevant technical field, or equivalent practical experience. PhD is a plus.

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.