Principal CPU Architect - High-Performance and Physical Design
NVIDIAJob Title
Principal CPU Architect - High-Performance and Physical Design
Role Summary
Senior architect responsible for driving CPU microarchitecture decisions that enable very high frequency, high-performance server-class processors. The role spans architecture, RTL, circuit and standard-cell tradeoffs, physical design, process technology, and advanced packaging.
Work closely with RTL, physical design, power, packaging, and software teams to optimize frequency, power delivery, timing, thermal behavior, area, and implementation risk.
Experience Level
Senior level. The posting requests 15 or more years of relevant experience in CPU architecture and high-frequency server CPU design.
Responsibilities
Key responsibilities include translating architectural choices into implementable, high-frequency designs and defining power and physical-design methodology improvements.
- Bridge architecture, RTL implementation, and physical design to meet frequency and power targets.
- Act as subject-matter expert on power delivery, on-chip regulators, power gating, di/dt, and thermal throttling.
- Analyze power, timing, and thermal trade-offs for die stacking and advanced packaging proposals.
- Propose and drive improvements to high-frequency design practices and power methodology for custom CPU cores.
- Collaborate with process, circuit-design, RTL, verification, and software teams to align cross-domain constraints and optimizations.
Requirements
Must-have technical skills and experience; listed separately are preferred enhancements.
- Extensive experience in CPU architecture focused on high-frequency server CPU designs.
- Deep knowledge of power dissipation, power delivery systems, and efficiency considerations.
- Detailed understanding of process technologies and circuit-level design trade-offs.
- Experience with power management techniques spanning software, architecture, RTL, VLSI, and process.
- Practical experience assessing trade-offs related to advanced packaging and die stacking.
- Proven ability to translate microarchitectural and RTL decisions into frequency, timing, power, thermal, and area outcomes.
Nice-to-have:
- PhD or formal research experience in a related area.
- Advanced physical-design expertise and hands-on implementation experience.
- Familiarity with GPU and SoC design.
- Strong written and verbal communication skills for cross-functional collaboration.
Education Requirements
BS or MS in Electrical Engineering, Computer Science, Computer Engineering, or a related technical field, or equivalent practical experience. PhD is listed as a distinguishing preference.
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.
