GPU Validation Engineer

Top Mandatory Skills
- GPU platform validation: GPU driver installation, GPU enumeration, firmware compatibility and PCIe validation (topology and link checks) on data center GPUs.
- Workload and system validation: Functional, regression, stress and workload testing, including thermal, power, GPU utilization and memory validation.
- Server platform and BIOS validation: Bringing up and validating data center servers (Dell PowerEdge / Supermicro / HPE), including BIOS setup and validation.
- Firmware, BMC and driver validation: Validating BMC, firmware and drivers, including firmware version pairing and upgrade/downgrade paths.
- Hardware troubleshooting and root cause analysis: In-depth debugging of hardware, firmware and driver failures during bring-up and validation, such as boot/POST hangs, reset failures and enumeration issues.
- AI/HPC workload validation and characterization: Running and analyzing AI/HPC workloads, and measuring performance and stability.
- Linux and CLI skills: Hands-on with Ubuntu and RHEL, including OS installation and imaging, driver setup and command-line tools for system and GPU diagnostics.
- Log analysis and automation: Analyzing system, BMC and driver logs, running Python scripts and reviewing automation results.
- Availability: Flexibility to work weekends and extended hours when needed during critical release validation phases.

Nice-to-Have Secondary Skills
- Test planning: Writing test cases, test plans and coverage matrices for hardware, firmware, IP blocks and drivers.
- Multi-GPU and networking validation: Running collective communication benchmarks across multiple GPUs and nodes and validating high-speed NICs and RDMA.
- Virtualization: VMware ESXi, GPU passthrough and GPU partitioning.
- Scripting: Basic Python or shell scripting to automate tests and parse logs.
- Tools: Experience with Jira for test management and defect tracking.

Interview Rounds: 2
____________________
Job Description

About the Role
Were hiring a hands-on validation engineer to help bring up, qualify and stabilize next-generation data center GPU platforms used for AI and HPC workloads. Youll own system-level validation across GPU, CPU, firmware, networking and storage, from the first boot to large multi-GPU and multi-node workload testing. Youll work closely with firmware, BIOS, platform, driver and partner engineering teams to find, debug and resolve problems before production.

Key Responsibilities:
Platform bring-up and validation
- Bring up multi-GPU AI/HPC server platforms, including CPU, GPU, memory, NICs and storage.
- Validate GPU enumeration, PCIe topology, link training and device interoperability.
- Validate BIOS, IFWI, BMC and firmware pairings and upgrade/downgrade paths.
- Run stress and stability tests on boot, power cycles, warm and cold resets, and AC cycles.
AI and HPC workload validation
- Run and analyze collective communication benchmarks across multi-GPU and multi-node setups to measure bandwidth, latency and scaling.
- Characterize performance with HPC and AI workloads, GPU burn-in and vendor qualification suites.
- Monitor GPU utilization, power, thermals, memory health and platform stability under sustained load.
Networking and interconnect
- Validate high-speed NICs and RDMA / peer-to-peer GPU data paths.
Debug and root cause analysis
- Triage and debug hardware, firmware and driver failures, including boot/POST hangs, reset failures, link drops and RAS/MCA errors.
- Collect and analyze system, BMC and driver logs, and provide clear, reproducible defect reports to development teams.
Test planning and execution
- Write test cases for each release (BIOS/IFWI/driver drops).
- Run functional, regression, stress, performance and compatibility test cycles.
- Track defects through their lifecycle in Jira and report status, blockers and risks to program management.
Cross-functional collaboration
- Work with firmware, BIOS, platform, driver, OEM/ODM and silicon partner teams during co-validation and qualification.
- Help plan lab readiness, system allocation and release validation schedules, including support during bring-up phases.

Required Qualifications:
- B.E./B.Tech in Electronics, Electrical, Computer Science or a related field.
- 12+ years in hardware/software validation, including at least 2 years of data center GPU platform validation.
- Hands-on experience with data center GPUs.
- Strong knowledge of server platforms, BIOS, BMC, firmware and drivers.
- Experience with GPU drivers and GPU health/diagnostic tools.
- Strong Linux skills (Ubuntu, RHEL), including OS imaging, driver installation and log analysis.
- Working knowledge of PCIe and high-speed networking.
- Proven root cause analysis and defect triage skills.
- Familiarity with SDLC/STLC, Agile and tools such as Jira.

Preferred Qualifications:
- Experience with GPU virtualization (partitioning, GPU passthrough, VMware ESXi).
- Python or shell scripting for test automation and log parsing.
- Experience with multi-node cluster validation.

Key Competencies:
- A structured approach to debugging and attention to detail.
- Comfort working in a fast-paced pre-production lab.
- Ownership and a willingness to support critical bring-up milestones, including weekend and extended-hour support when needed.