Data Center Technician (Server & Fiber)

Sai Kumar Reddy Kandi

OHIO 779-***-**** **************@*****.***

SUMMARY

Data Center Technician with 5+ years of hands-on server hardware break/fix across a hyperscale site at AWS, a multi- tenant colocation facility at Cologix, and an enterprise hosting data center at Web Werks. Currently supporting 1,000+ rack units on 24/7 shift with on-call rotation. Core work: component-level diagnostics and replacement on Dell PowerEdge, HP ProLiant, and NVIDIA H100 GPU systems, Linux host recovery, and Layer 1/2 fiber and copper troubleshooting. Track record includes 200-300 incidents a month at 98% first-call resolution within SLA, 99.9% documented uptime, 75+ rack-and-stack deployments, and a 40% reduction in RMA turnaround. M.S. in Computer Science, with Bash and Python automation for diagnostics and health checks. SKILLS

Server Hardware: Dell PowerEdge, HP ProLiant, NVIDIA H100 GPU baseboards, GPUs, CPUs, DIMMs, motherboards, NICs, heatsinks, power supplies

Troubleshooting: Component-level hardware break/fix, POST codes, memory error logs, console diagnostics, root cause analysis, isolation testing, RMA staging and failed-part returns Storage: HDD, SSD, NVMe, SMART analysis, drive firmware, partitioning and mounting, secure wipe for decommissioning

Networking & Cabling: Layer 1/2 troubleshooting, port flapping, link errors, port mapping, ANSI/TIA fiber and copper structured cabling, fiber cleaning and reseating, SFP/QSFP, DAC, RJ45, patch panels, MMR cross-connects, switches and routers, VLANs, subnetting, TCP/IP Linux & Systems: Linux/UNIX CLI, dmesg, journalctl, smartctl, lsblk, ipmitool, boot and filesystem repair, kernel modules and drivers, Kickstart/PXE/DHCP imaging troubleshooting, patch management, Bash, Python, Windows Server

Server Management: IPMI, iDRAC, iLO remote console, firmware maintenance windows Data Center Operations: 24/7 shift and on-call, rack-and-stack, high-density AI/cloud deployments, hot/cold aisle containment, decommissioning and chain of custody, CMDB and asset management, MOP/CMOP, SOPs and runbooks, cloud on-ramp cross-connects to AWS, Azure, and Google Cloud, SOC 1/2, HIPAA, PCI-DSS

Tools & Platforms: Jira, ServiceNow, Confluence, SharePoint, Cologix Command DCIM, Nagios, PRTG, C- CURE 9000, Fluke testers, OTDR, light meters, INLOGIX PROFESSIONAL EXPERIENCE

Amazon Web Services, Portland, OR 06/2026 - Present Data Center Technician

• Restore production capacity across 1,000+ rack units in a 24/7 hyperscale facility, diagnosing and replacing failed GPUs, CPUs, GPU baseboards, motherboards, DIMMs, NICs, heatsinks, SSDs, and HDDs. Confirm every fault with SMART data, memory error logs, and console diagnostics before a part comes out.

• Service and validate NVIDIA H100 GPU baseboards on high-density AI/ML compute, averaging 25+ GPU hosts a month through component-level diagnostics and post-install verification that return accelerated-compute systems to fleet availability.

• Troubleshoot Linux hosts at the OS level: failed boots, corrupt filesystems, bad mounts, full disks, driver and kernel module faults, interfaces that will not come up, and hung services. Escalate with dmesg and console output attached.

• Resolve port flapping, down ports, and dead links by tracing runs, cleaning and reseating fiber, re-terminating copper, and replacing RJ45, DAC, SATA, UART, and fiber cabling instead of swapping components blind.

• Install SSDs and NVMe drives into production servers; verify detection at firmware and OS level, partition, mount, and validate host health before returning the host to service.

• Support engineering on Kickstart auto-build nodes that fail to image by checking PXE and DHCP handoff, NIC link, disk detection, and console output.

• Own Tier 1 through Tier 3 tickets end to end, sequencing the queue by business impact so the highest-severity outages clear first, and coordinating manual requests with network, logistics, and engineering teams.

• Perform RCA and isolation testing on repeat hardware and connectivity failures, escalating to engineering and vendors with documented evidence rather than replacing the same part again.

• Decommission nodes: de-cable, pull drives, update asset records, and stage hardware for pickup under chain of custody.

• Provide 24/7 response and on-call coverage for severity alerts, and complete installs outside quarterly growth scope with structured cabling, port labeling, and rack-level documentation per runbooks and SOPs.

• Automate recurring diagnostics and reporting with Bash scripting, reducing manual technician effort on repetitive tasks.

Cologix, Ashburn, VA 05/2025 - 05/2026

Data Center Technician

• Performed break/fix on drives, DIMMs, NICs, and power supplies across Dell PowerEdge and HP ProLiant servers, and installed SSD and NVMe drives during customer storage upgrades.

• Monitored 500+ rack units through Cologix Command DCIM with 24/7 alarm response and on-call coverage on a multi-tenant colocation floor, sustaining 99.9% documented uptime.

• Troubleshot Linux on customer and internal hosts using dmesg, journalctl, smartctl, lsblk, and interface state to separate host faults from cabling and switch-port problems; recovered hosts over remote console when they dropped off the network.

• Isolated fiber and copper faults with Fluke testers, OTDRs, light meters, and INLOGIX, clearing customer-reported latency and link errors at the cable plant.

• Resolved port flapping and down ports in customer cages by testing at the patch panel and switch port, cleaning and reseating optics, and replacing bad patch cords and DACs.

• Cut average RMA component turnaround 40% by rebuilding spare-parts inventory and migrating tracking to an electronic system.

• Provisioned physical and virtual cross-connects to AWS, Azure, and Google Cloud through Cologix Fabric, and executed MMR cross-connects and live service swaps that accelerated customer turn-up timelines.

• Decommissioned customer nodes and cabinets: pulled drives, de-cabled, released rack space, and updated asset records for pickup.

• Documented port maps, network maps, runbooks, and site procedures in SharePoint under MOP/CMOP, recording every infrastructure change to prevent maintenance-window downtime.

• Audited rack locks, cage integrity, and biometric access points and responded to C-CURE 9000 unauthorized-access alarms to uphold SOC 1/2, HIPAA, and PCI-DSS compliance. Web Werks India Pvt. Ltd., Hyderabad, India 10/2019 - 05/2023 Data Center Technician

• Maintained Dell PowerEdge and HP ProLiant fleets across 300+ rack units in a 24/7 enterprise hosting operation, holding 99.9% uptime for business-critical services.

• Led 75+ rack-and-stack deployments covering equipment mounting, structured cabling, cable management, port labeling, and hot/cold aisle containment.

• Replaced failed drives, memory, NICs, and power supplies with downtime held under 2 hours per incident, and installed SSDs during storage refreshes.

• Resolved 200 to 300 incidents and service requests a month in Jira at 98% first-call resolution within SLA.

• Troubleshot Linux across 300+ servers: boot and filesystem failures, permission and mount errors, disk-full conditions, failed services, and dead interfaces. Executed OS patch and firmware maintenance windows.

• Traced Layer 1 faults including bad patch cords, dirty fiber, and loose optics, restoring links without unnecessary part swaps.

• Configured Nagios and PRTG alerting for bandwidth, packet loss, and device uptime across 300+ servers to surface degradation before customer impact.

• Wrote Bash and Python scripts for log collection and routine health checks.

• Trained and mentored 5+ new technicians on critical workflows and safety practices, and authored SOPs and runbooks in Confluence.

EDUCATION

• Master of Science, Computer Science, Northern Illinois University, DeKalb, IL

• Bachelor of Technology, Electronics and Communication Engineering, Vel Tech Rangarajan Dr. Sagunthala R&D Institute, Chennai, India

Contact this candidate