High Performance Computing Administrator II

Education and Experience Requirements

Bachelor's Degree Engineering, Computer Science, Information Technology, or related curriculum or equivalent combination of education and experience sufficient to successfully perform the essential functions of the job. A Masters degree may be used to offset one year experience requirement; PhD may offset two years of experience. 5 years experience required. in HPC or scientific computing environment to include the installation, configuration and maintenance of Redhat Package Manager (RPM)-based Linux distributions (RedHat, SuSE).

Position Purpose:

Assist senior leadership in the High Performance Computing (HPC) group of the Advanced Computing Technologies (ACT) department in establishing the operating plan and technical specifications to leverage enabling technologies in meeting the desired goals, objectives, and strategies of the Computational Fluid Dynamics, Simulation, and Modeling Engineering business areas. Provide the appropriate leadership and technical oversight for implementing the operational plan. Responsible for leading the optimum integration of scientific applications to high performance computing technology.

Job Description

Principle Duties and Responsibilities:

Essential Functions:

1. Assume the responsibility for the day-to-day operations of Gulfstream's production HPC cluster.
2. Troubleshoots and maintains the Infiniband and Ethernet networks.
3. Understands, maintains and supports high performance parallel storage systems.
4. Assists end users running applications on the HPC cluster.
5. Provides third level support for end users who experience problems on engineering workstations and remote visualization systems.
6. Assists with the mentoring and professional development of junior level HPC Administrators.
7. Manage, maintain, monitor, and control interactive and batch processes, both scheduled and unscheduled (including on-request processing).
8. Complete engineering-defined batch processing and backups in the correct sequence and within the established time periods.
9. On an ongoing basis, suggest improvements to processing capabilities and efficiencies through system tuning and other hardware and software optimizations and improvements.
10. Perform regular monitoring of utilization needs and efficiencies, and report regularly on tuning initiatives.
11. Perform proactive failure trend analysis and root cause analysis for all system failures.
12. Produce trend reports to highlight production issues and follow predetermined action and escalation procedures when issues are encountered.
13. Monitor, verify, and make appropriate adjustments to support proper application executions.
14. Provide technical solutions that meet the performance and processing objectives of the business areas.
15. Perform upgrades thoroughly and accurately that comply with corporate policies and industry best practices.
16. Provide leadership to junior level HPC Administrators during system upgrades and outages.

Additional Functions:

1. Maintain technical relationships with multiple hardware and software vendors. .
2. Work multiple operational windows as required. to support business objectives. .
3. Provide on-call support 24x7 .
4. Develop and implement technical standards, hardware standards, and software standards. .

Perform other duties as assigned.

Other Requirements:

1. Experience with management of infiniband-based Linux-based HPC clusters, high performance parallel storage, and configuration and management of cluster scheduling software.
2. Experience managing High Performance Computing low-latency, high-bandwidth interconnects.
3. Experience supporting Linux based scientific workstations running visualization applications.

This job requires one to be able to read, write, speak, and understand the English language.