Director, Rack Scale Software Architecture

Details

NVIDIA has been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. Today NVIDIA is tapping into the unlimited potential of AI to define the next era of computing. The Rack Scale Software Architecture team works on data center platform & node designs from single-node HGX/DGX systems up to large multi-node NVLink domain rack architectures. These designs bring together NVIDIA GPUs, NVLink, NVIDIA InfiniBand networking, NVIDIA Grace CPUs, and a fully optimized NVIDIA AI and HPC software stack.

This role is a technical management position responsible for rack-scale system software architecture across firmware, kernel drivers, operating systems, networking, fabrics, user-mode drivers, and manageability software. The role requires working with internal component leads and engaging hyperscaler / cloud service providers to bring products to market.

Responsibilities

• Drive end-to-end software architecture for NVIDIA's rack-scale products.
• Maintain deep understanding of the product portfolio and roadmap; translate plans into formal software requirements that anchor execution across the organization.
• Ensure high quality and reliable software; serve as a trusted architectural partner to teams requiring guidance or oversight.
• Work directly with major customers to understand their requirements and align roadmaps.
• Present team vision to senior NVIDIA and external leaders using strong communication skills.
• Provide technical leadership and career mentorship to the team.
• Make key technical decisions even when faced with ambiguity.

Requirements

• BS or MS degree in Computer Engineering, Computer Science, or related degree or equivalent experience.
• 15+ years overall experience in system architecture and design with 8+ years of proven management experience.
• Deep experience designing architecture for scalable and performant server systems, particularly at the software/hardware interface.
• Proven leadership skills and strong ownership on past projects involving a large, sophisticated code base.
• Previous experience working with complex system software for accelerators such as GPUs, DPUs, or FPGAs.
• Strong managerial, problem solving and critical thinking skills.
• Comfortable operating in highly matrixed organizations while holding a leadership position.
• Strong interactive, verbal and written communications skills.

Ways to stand out

• Knowledge of large-scale cloud and cluster-level deployment and management systems; experience designing robust, resilient and performant scale-up fabrics.
• Demonstrated track record of leading data center products across lifecycle stages: inception, pre-silicon development, post-silicon bring-up, manufacturing, and deployment.
• Strong understanding of networking technology & protocols (e.g., Ethernet, InfiniBand). Familiarity with CXL, UCIe and other chip-to-chip (C2C) architectures. Knowledge in storage and networking technologies.

Compensation and benefits

• Base salary range: 320,000 USD - 488,750 USD (determined based on location, experience, and pay of employees in similar positions).
• Eligible for equity and benefits.

Additional information

• Applications accepted at least until June 2, 2026.
• This posting is for an existing vacancy.
• NVIDIA uses AI tools in its recruiting processes.
• NVIDIA is an equal opportunity employer committed to fostering an inclusive work environment.