Roles & Responsibilities¶

This section outlines my key roles and responsibilities in supporting large-scale Linux and high-performance computing (HPC) environments in production settings.

HPC Operations & Administration¶

Manage and support multi-petaflop HPC environments for research workloads.
Perform tasks like setting up and managing compute nodes, from installation to decommissioning.
Support workload scheduling using PBS Pro to ensure tasks run smoothly in shared environments.
Ensure stable job execution across both CPU and GPU-based clusters.

System Monitoring & Reliability¶

Monitor system health and availability using tools like NVIDIA Bright Cluster Manager, Dell OpenManage Enterprise, and InfiniBand UFM.
Run proactive health checks to identify potential issues in hardware, networks, or systems.
Respond to alerts and incidents to minimize disruptions and maintain system uptime.
Ensure high availability of systems in 24×7 production environments.

Performance Validation & Optimization¶

Run performance benchmarks using tools like HPL, LINPACK, and HPCC.
Validate performance after system upgrades, changes, or new deployments.
Work on fine-tuning system performance to meet operational goals.

Application & User Support¶

Install, configure, and validate both commercial and open-source applications in HPC environments.
Support running applications that use MPI for multi-node execution.
Manage environment modules and application runtime settings to ensure smooth operation.
Provide user onboarding, access management, and technical support to researchers and engineers.

Automation & Operational Efficiency¶

Write shell scripts to automate common administrative tasks.
Automate processes like OS provisioning, user management, and software deployment.
Streamline operations to improve consistency and reduce manual effort.

Hardware & Infrastructure Support¶

Assist with server installation, integration, and validation in datacenter environments.
Perform BIOS, firmware, and driver upgrades on Dell PowerEdge platforms.
Troubleshoot hardware issues and assist with diagnostics and repairs.
Help coordinate infrastructure changes during upgrades and system expansions.

Networking Support¶

Manage high-speed InfiniBand (400 Gb/s) networking for HPC clusters.
Monitor network health, fix connectivity issues, and optimize performance.
Ensure network readiness for running large-scale parallel workloads.

Incident Management & Documentation¶

Provide L2-level incident support in high-availability environments.
Analyze and troubleshoot system issues, then take corrective actions.
Document incidents, solutions, and operational procedures for future reference.
Support activities related to system changes and updates.

Datacenter & Project Support¶

Contribute to projects aimed at datacenter modernization and infrastructure deployment.
Support tasks like server installation, OS provisioning, and network setup.
Work closely with cross-functional teams during project execution and handover.