Senior Technical Support Engineer (L3) at Supermicro (2025-04 – 2026-07)
- Served as the primary owner of field diagnostic USB images for nearly all NVIDIA GPU server platforms, obtaining platform-specific PartnerDiag packages through the NVIDIA partner portal, building bootable Linux images, and validating them on target systems before field release.
- Built and qualified separate DCGM-based USB images for thermal troubleshooting on NVIDIA H200 and B200 systems, complementing standard PartnerDiag coverage.
- Provided L3 support for NVIDIA and AMD GPU platforms, combining escalated log analysis with hands-on failure reproduction, system testing, and component-level isolation.
- Supported field engineers remotely with diagnostic execution, log collection, cross-testing, and isolation across GPUs, PCIe slots, GPU trays, baseboards, networking, power, and cooling components.
- Analyzed BMC, SEL, Redfish, Linux, NVIDIA, AMD, and diagnostic logs to identify likely fault domains and recommend corrective actions, additional testing, or RMA.
- Troubleshot BIOS, BMC, CPLD/FPGA, firmware, GPU driver, Fabric Manager, NVLink/NVSwitch, ConnectX, InfiniBand/Ethernet, PCIe, storage, power, and thermal issues.
- Collaborated with L1/L2 support, field service, engineering, manufacturing, customers, and technology partners to resolve complex and intermittent server issues.
GPU Test and Validation Engineer (Board-Level Test) at Wipro – NVIDIA Assignment (2019-01 – 2024-12)
- Designed and executed diagnostic and validation tests for multiple generations of Tesla GPUs.
- Developed and maintained automation scripts using Python and Shell, improving test efficiency.
- Provided onsite support and technical guidance for Gen3/Gen4/Gen5 GPU testing and validation.
- Collaborated with global teams to resolve firmware issues and optimize system performance.
- Utilized GCC toolchains and GDB for debugging and software validation.
- Conducted inter-process communication (IPC) analysis for GPU-based systems.
Senior Software QA (Validation) Engineer, UNIX Center at FUJITSU (2000-07 – 2018-12)
- Led QA testing for Solaris OS, ensuring reliability and performance of Fujitsu UNIX servers.
- Conducted hardware validation and system debugging, resolving complex system errors.
- Managed test schedules and collaborated with cross-functional engineering teams.
