High Performance Computing Administrator III

ARIES AERO SYSTEMS; Savannah (GA); On-site; USD 110,000 - 160,000; Full time

Job summary

ARIES AERO SYSTEMS is seeking an experienced HPC Systems Administrator to own the production HPC cluster, support end users, and lead upgrades. You will manage batch processing, tuning, and proactive failure analysis to ensure peak performance for CFD/Simulation workloads.

The role requires 7+ years in HPC environments, strong Linux skills, and experience with InfiniBand interconnects and cluster scheduling. On-site Savannah, GA with potential on-call responsibilities.

Qualifications

• Bachelor's degree in a related field required; advanced degree offsets years of experience.
• 7+ years in an HPC or scientific computing environment with Linux RPM distributions.
• Experience managing InfiniBand-based Linux HPC clusters and HPC storage.
• Experience with cluster scheduling software and visualization workstations.

Responsibilities

• Own day-to-day operations of the production HPC cluster.
• Support end users running applications on the HPC cluster.
• Provide third-level support for engineering workstations and remote visualization systems.
• Manage, maintain, monitor, and control interactive and batch processes (scheduled and unscheduled).
• Ensure batch processing and backups complete correctly and on schedule.
• Improve processing capabilities and efficiency through system tuning and optimization.
• Monitor utilization and report on tuning initiatives.
• Perform proactive failure trend analysis and root cause analysis for system failures.
• Produce trend reports and follow escalation procedures for production issues.
• Monitor and adjust systems to support proper application execution.
• Provide technical solutions meeting performance and processing objectives.
• Perform upgrades per corporate policy and industry best practices.
• Lead HPC Administrators during system upgrades and outages.
• Create thorough upgrade plans.
• Support introduction of new technologies to improve capability, productivity, and cost of ownership.
• Participate in HPC technical solution design.
• Evaluate efficiency, technology effectiveness, and interoperability on an ongoing basis.
• Maintain relationships with hardware/software vendors.
• Work multiple operational windows as required; provide 24x7 on-call support.
• Support development and implementation of technical, hardware, and software standards.

Skills

HPC Administration

Linux System Admin

InfiniBand Networking

Cluster Scheduling

Performance Tuning

Education

Bachelor's degree in Engineering, Computer Science, Information Technology, or related field

Master's degree may offset 1 year of experience

Tools

RPM-based Linux (RedHat/SuSE)

InfiniBand HPC interconnects

System monitoring tools

Storage management

Job description

Contribute to the strategic objectives of the High Performance Computing environment in the Advanced Computing Technologies department for our client, a leading business aviation aircraft manufacturer. Develop operational plans, goals, and strategies to best serve the Computational Fluid Dynamics, Simulation, and Modeling Engineering business units. Provide technical oversight and operational support to ensure continued sustained functionality of the HPC environment, and drive optimum integration of scientific applications to HPC technology.

Principal Duties and Responsibilities

• Own day-to-day operations of the production HPC cluster
• Support end users running applications on the HPC cluster
• Provide third-level support for engineering workstations and remote visualization systems
• Manage, maintain, monitor, and control interactive and batch processes (scheduled and unscheduled)
• Ensure batch processing and backups complete correctly and on schedule
• Improve processing capabilities and efficiency through system tuning and optimization
• Monitor utilization and report on tuning initiatives
• Perform proactive failure trend analysis and root cause analysis for system failures
• Produce trend reports and follow escalation procedures for production issues
• Monitor and adjust systems to support proper application execution
• Provide technical solutions meeting performance and processing objectives
• Perform upgrades per corporate policy and industry best practices
• Lead HPC Administrators during system upgrades and outages
• Create thorough upgrade plans
• Support introduction of new technologies to improve capability, productivity, and cost of ownership
• Participate in HPC technical solution design
• Evaluate efficiency, technology effectiveness, and interoperability on an ongoing basis
• Maintain relationships with hardware/software vendors
• Work multiple operational windows as required; provide 24x7 on-call support
• Support development and implementation of technical, hardware, and software standards

Experience and Education Requirements

• Bachelor's degree in Engineering, Computer Science, Information Technology, or related field required (or equivalent combination of education/experience)
• Master's degree may offset 1 year of experience; PhD may offset 2 years
• 7 years of experience in an HPC or scientific computing environment, including installation, configuration, and maintenance of RPM-based Linux distributions (RedHat, SuSE)
• Experience managing InfiniBand-based Linux HPC clusters, high-performance parallel storage, and cluster scheduling software
• Experience managing HPC low-latency, high-bandwidth interconnects
• Experience supporting Linux-based scientific workstations running visualization applications