Lead Performance Modeling Architect, CPU Fabric and LLC
NVIDIAJob Title
Lead Performance Modeling Architect, CPU Fabric and LLC
Role Summary
Technical lead responsible for driving performance modeling of cache hierarchies and coherent I/O interconnects across automotive and data center platforms. The role combines hands-on modeling, cross-functional liaison with Architecture/RTL/Software teams, and people leadership for a team of performance-modeling engineers.
Experience Level
Senior — requires substantial industry experience. The posting specifies 8+ years in high-performance silicon architecture and experience managing technical teams or complex projects.
Responsibilities
Primary responsibilities include defining modeling strategy, leading the modeling team, and resolving cross-team performance trade-offs.
- Define long-term vision and approach for modeling infrastructure (cycle-accurate, analytical, stochastic, hybrid).
- Lead and mentor a team of modeling engineers; conduct code and architecture reviews.
- Serve as primary liaison between Architecture, RTL build, and Software to diagnose and resolve performance bottlenecks.
- Drive adoption of advanced methodologies (emulation/simulation hybrids, AI-based optimization) to accelerate delivery.
- Plan and prioritize simulation workloads and engineering effort across multiple concurrent projects in automotive and data center domains.
Requirements
Must-have technical skills and experience; items marked as Nice-to-have where applicable.
- Must-have: 8+ years in high-performance silicon architecture or performance modeling; demonstrated experience managing technical teams or complex projects.
- Must-have: Deep knowledge of cache-coherency protocols (e.g., AMBA CHI, MESI), memory sub-systems, and high-speed interconnect fabric design.
- Must-have: Significant experience architecting and implementing large-scale simulators in C++ or SystemC, focused on modularity and speed.
- Must-have: Competence using statistical analysis to validate model accuracy against RTL or silicon and to explain performance cliffs to stakeholders.
- Nice-to-have: Full-stack experience from high-level modeling to RTL integration and post-silicon tuning.
- Nice-to-have: Participation or influence in industry standards bodies (e.g., CXL Consortium) or a record of published architectural research.
- Nice-to-have: Proven scalability work across both low-latency safety-critical systems and large high-bandwidth cloud-scale networks.
Education Requirements
Master's or Ph.D. in Computer Engineering or a related 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.
