GPU/SOC Low-Power Feature Architect - HSIO
NVIDIAJob Title
GPU/SOC Low-Power Feature Architect - HSIO
Role Summary
Join NVIDIA's Silicon Co-Design Group (HW ArchDev team) to define and deliver next-generation high-speed IO features, with emphasis on NVLink and NVLink-C2C interoperability and power efficiency. The role spans architecture, bring-up, debug, and system integration across silicon and platform teams.
Base salary ranges: $168,000–$264,500 (Level 4) and $196,000–$310,500 (Level 5); final base depends on location, experience, and internal pay bands.
Experience Level
Senior — minimum 10 years of experience working on high-speed IO (HSIO) in roles such as power management, bring-up, performance/power modeling, or system debug.
Responsibilities
Primary responsibilities include architecture and implementation of HSIO features, power optimization, and cross-team debug to enable reliable, energy-efficient interconnects.
- Contribute to design and architecture of next-generation high-speed IOs (NVLink, NVLink-C2C).
- Drive IO power optimization and energy-efficiency improvements across use cases.
- Ensure interoperability with connected devices and complex interconnect topologies.
- Lead deep technical investigations into HSIO bugs and coordinate multi-team debug activities.
- Collaborate with system architects, mixed-signal and design teams, software/firmware, QA, operations, and application engineering through development and release.
Requirements
Core technical and leadership requirements for immediate impact.
Must-have:
- Minimum 10 years of hands-on HSIO experience covering power management, use-case analysis, perf/power modeling, bring-up, or debug.
- Experience with system-level and interconnect power-management optimizations and silicon/platform power modeling for active and idle scenarios.
- Understanding of firmware/driver structures and HW interaction.
- Strong fundamentals in electrical engineering and computer architecture, including high-speed interfaces, timing analysis, process variation, statistical error rates, and power analysis.
- Proven influence and ability to lead cross-functional teams to a unified technical outcome.
Nice-to-have:
- Prior work on NVLink or similar high-speed interconnects and platform-level system integration.
- Experience with DGX or data-center scale system requirements and constraints.
Education Requirements
BS or MS in Electrical Engineering (EE) or Computer Engineering (CE), or equivalent practical experience; the posting explicitly allows equivalent experience in lieu of a degree.
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.
