GPU Platform SME

Lenovo•Morrisville, NC

About The Position

Lenovo Infrastructure Solutions Group is seeking a GPU Systems Validation Engineer to develop and validate next-generation AI and accelerated computing platforms. The role validates GPU technologies across server, rack, and cluster environments, collaborating with GPU architects, hardware and firmware teams, and technology suppliers to ensure platform readiness, performance, reliability, and scalability for enterprise and hyperscale deployments. The position covers GPU platform architecture and validation strategy, readiness and infrastructure planning, system bring-up and process development, validation execution, failure analysis, and cross-functional and supplier collaboration. The engineer leads validation at node (L10), rack (L11), and cluster (L12) levels, develops and executes test plans, and owns technical issues from discovery and triage through root cause analysis, corrective action, and closure.

Requirements

Bachelor's degree in Electrical Engineering, Computer Engineering, Computer Science, Computer and Information Science, or a related technical discipline.
At least 6 years of experience in server platform development, system validation, system integration, hardware validation, AI infrastructure, or a related engineering discipline.
Strong knowledge of enterprise server architecture and system integration, including BIOS/UEFI, BMCs, operating systems, CPU and memory subsystems, storage, networking, PCIe devices, firmware, device drivers, and software applications.
Strong understanding of GPU interconnect and high-speed networking technologies, including PCIe, Ethernet, InfiniBand, NVLink, NVSwitch, and related GPU fabric technologies.
Hands-on experience with system integration testing, functional validation, stress testing, performance testing, failure analysis, troubleshooting, and root cause investigations.
Working knowledge of Linux administration, command-line diagnostics, log analysis, and server troubleshooting methodologies and tools.
Ability to independently drive complex technical issues from identification through root cause determination and resolution.
Strong written and verbal communication skills and ability to collaborate across global cross-functional engineering teams.

Nice To Haves

Hands-on experience with advanced AI infrastructure platforms such as NVIDIA HGX, NVIDIA DGX, GB200, GB300, NVL72, or next-generation GPU architectures.
Experience with rack-scale AI systems, GPU clusters, and large-scale accelerated computing environments using NVLink, NVSwitch, InfiniBand, or high-speed Ethernet fabrics.
Experience supporting hyperscale, cloud, AI infrastructure, OEM, ODM, server development, manufacturing validation, or large-scale data center deployments.
Familiarity with NVIDIA validation and diagnostic tools such as DCGM, NVDiag, and NVQual.
Experience with NVIDIA CUDA, AMD ROCm, or other GPU software ecosystems.
Experience developing validation automation, diagnostic solutions, or validation frameworks using Python, Shell scripting, or similar languages.
Familiarity with liquid cooling infrastructure, power distribution systems, rack integration technologies, and data center deployment considerations.
Experience collaborating directly with GPU suppliers, hyperscale customers, ODM/OEM partners, or global engineering organizations.
Mandarin language capability.

Responsibilities

Study next-generation GPU platform architectures, reference designs, and supplier documentation to understand platform capabilities, changes, and validation requirements.
Compare platform generations and identify validation impacts, readiness gaps, risks, and infrastructure requirements.
Review supplier validation requirements and Lenovo validation strategies to determine execution prerequisites and coverage plans.
Translate platform requirements into executable validation strategies with GPU architects and engineering stakeholders.
Define and coordinate validation environment requirements, including lab infrastructure, test equipment, fixtures, software tools, utilities, licenses, and system configurations.
Review validation plans and test requirements across Platform Architecture, Electrical Engineering, Enterprise Architecture, Thermal Engineering, and Reliability Engineering.
Establish validation readiness plans for new platform introductions and technology transitions, and support validation framework deployment and test environment setup.
Develop system bring-up processes, work instructions, validation procedures, and standard operating procedures with GPU architects and engineering teams.
Establish test methodologies, execution processes, and validation best practices for consistent and repeatable results.
Lead validation activities for GPU-enabled server platforms at node (L10), rack (L11), and cluster (L12) levels.
Execute system integration, functional, stress, performance, scalability, and reliability testing.
Develop and execute validation plans covering hardware, firmware, operating systems, networking, storage, management controllers, device drivers, and GPU subsystems.
Validate GPU interconnects, high-speed networking fabrics, rack integration, power delivery systems, cooling solutions, and cluster deployments.
Own technical issues through discovery, triage, experiment design, failure reproduction, root cause analysis, corrective action identification, and validation closure.
Investigate hardware, firmware, software, and infrastructure issues using log analysis, diagnostics, system telemetry, and structured debugging techniques.
Conduct technical experiments and data-driven analysis to isolate failures and determine root cause; drive resolution with engineering teams and validate corrective actions.
Collaborate with engineering, manufacturing, product development, GPU supplier, ODM/OEM, hyperscale customer, and global engineering teams.
Support technical reviews, milestone readiness assessments, and product release activities.