Architect - GPU Performance
NVIDIAJob Title
Architect - GPU Performance
Role Summary
Work on system- and chip-level performance for next-generation GPUs and SoCs. The role analyzes performance bottlenecks across CPU, memory, interconnect and GPU subsystems and delivers models, workloads and infrastructure to guide architecture and design decisions.
Experience Level
Senior. The posting requests 3+ years of relevant experience in performance analysis and complex SoC/GPU architectures.
Responsibilities
Primary responsibilities include performance analysis, modelling, test development, and collaboration with architecture and design teams.
- Perform system-level performance and bottleneck analysis of high-performance GPUs and SoCs.
- Develop and use hardware models at multiple abstraction levels (performance models, RTL testbenches, emulators, silicon) to analyze performance.
- Create workloads and test suites targeting graphics, ML, automotive, video and computer-vision use cases.
- Collaborate with architecture and design teams to evaluate trade-offs for performance, area, and power.
- Develop infrastructure: performance models, testbench components, and analysis/visualization tools.
- Improve methodologies for representative datasets, faster turnaround, and early-stage performance analysis.
Requirements
Must-have technical skills and practical experience for the role. Nice-to-have items are listed separately.
- 3+ years of experience with performance analysis and exposure to complex SoC and/or GPU architectures.
- Strong understanding of SoC architecture, graphics pipeline, memory subsystem architecture, and NoC/interconnect concepts.
- Proficient in programming (C/C++) and scripting (Perl or Python).
- Strong debugging and data/statistical analysis skills; experience using RTL dumps for failure analysis.
- Nice-to-have: exposure to Verilog/SystemVerilog, SystemC/TLM, emulators, and silicon bring-up.
- Nice-to-have: experience developing performance simulators and cycle-accurate or approximate models for pre-silicon analysis.
Education Requirements
BE/BTech or MS/MTech in a relevant technical field; PhD is a plus. Equivalent practical experience is acceptable.
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.
