GPU Platform SME

Position Overview

Lenovo Infrastructure Solutions Group (ISG) is seeking an experienced GPU Platform SME to help evaluate, develop, validate, and optimize next-generation GPU-based AI infrastructure platforms.

In this role, you will work closely with GPU architects, platform engineering teams, and GPU suppliers to define and execute integrated validation strategies across node-level (L10), rack-level (L11), and cluster-level (L12) environments. You will be responsible for studying emerging GPU platform architectures, ensuring validation readiness, executing complex validation activities, and driving technical issues from discovery through root cause analysis and resolution.

This role requires a strong foundation in enterprise server architecture, system integration, and validation engineering, with experience owning validation activities across hardware, firmware, software, networking, and infrastructure domains. The successful candidate will serve as a technical leader for platform validation efforts, driving issue triage, debug investigations, cross-functional collaboration, and validation closure for advanced AI and accelerated computing platforms.

The ideal candidate combines expertise in server platform architecture, system validation, failure analysis, AI infrastructure, GPU technologies, and high-speed networking with the ability to evaluate new technologies, identify risks, and share technical knowledge across global engineering organizations.

Job Responsibilities

GPU Platform Architecture & Validation

• Evaluate next-generation GPU and AI infrastructure platforms to understand architecture changes, validation requirements, risks, and deployment considerations.
• Partner with architects, engineering teams, and suppliers to develop validation strategies and qualification plans.
• Serve as a technical SME for emerging GPU technologies and share knowledge across the broader engineering organization.

Validation Execution & Ownership

• Lead validation activities across node (L10), rack (L11), and cluster (L12) environments.
• Execute system integration, functional, stress, performance, reliability, and scalability testing for AI server platforms.
• Own validation programs from planning through execution, milestone completion, and validation closure.

Failure Analysis & Debug

• Drive technical issues from identification through triage, root cause analysis, corrective actions, and resolution.
• Investigate hardware, firmware, software, networking, storage, and infrastructure issues using structured debugging methodologies.
• Coordinate issue resolution across BIOS, BMC, hardware, firmware, networking, and software teams.

Cross-Functional Collaboration

• Work closely with global engineering teams, suppliers, ODM/OEM partners, and technology stakeholders.
• Support technical reviews, validation readiness assessments, and product release activities.
• Collaborate across North America and Asia to drive timely issue resolution and product quality.

Basic Qualifications

• Bachelor's degree in Electrical Engineering, Computer Engineering, Computer Science, or a related technical discipline.
• 6+ years of experience in server platform development, system validation, hardware validation, system integration, AI infrastructure, or related engineering fields.
• Strong knowledge of enterprise server architecture, including CPU, memory, storage, networking, BIOS/BMC, PCIe, operating systems, and firmware.
• Hands-on experience with system integration testing, platform validation, stress/performance testing, failure analysis, root cause investigation, and debugging.
• Proven ability to independently drive complex technical issues and collaborate effectively across global cross-functional engineering teams.
• Working knowledge of Linux systems, command-line diagnostics, log analysis, and server troubleshooting.

Preferred Qualifications

• Experience with NVIDIA-based AI infrastructure platforms, including HGX, DGX, GB200, GB300, NVL72, or similar GPU server architectures.
• Knowledge of NVLink, NVSwitch, InfiniBand, high-speed Ethernet fabrics, GPU clusters, and large-scale AI environments.
• Experience with NVIDIA diagnostic and validation tools such as NVDiag, DCGM, NVQual, or equivalent tools.
• Experience supporting hyperscale, cloud, OEM/ODM, AI infrastructure, or enterprise server validation environments.
• Experience evaluating next-generation technologies and serving as a technical lead or SME for platform validation initiatives.
• Bilingual English and Mandarin language capability is highly preferred.