HPC Systems Administrator

Job Summary

Manages and supports high performance computing clusters, computational computing infrastructures and specialized research, science, engineering, and mathematics applications used in computational computing environments. Supports management, tuning, operating systems, parallel file systems, automating deployment of compute nodes, managing and tuning specialized storage environments, login nodes, and HPC scheduling systems.

• Administers and supports server operating systems and research application environments. Includes compiling, installation and testing of patches, performance monitoring, and tuning.
• Assists the IT Associate Director implementing computational technology projects.
• Manages infrastructure such as cabling, storage system, SAN switches, infiniband switches, network switches, server racks, and rack power infrastructure.
• Provides support for end user service requests.
• Interprets and implements policies and procedures as they apply to an assigned area.
• May recommend changes on policy and procedures as necessary.
• Performs essential duties in any emergencies such as hurricanes, public health emergencies, and/or any other university emergency closing. The employee is expected to be available to report to work as needed during university emergency closing with appropriate notification of a department administrator.
• Troubleshoots and resolves complex systems or application issues.
• Works closely with the IT Associate Director in managing the HPC job scheduler.
• Manages computational computing storage systems, including parallel file systems.
• Uses tools, scripts or programming, the automation of routine tasks are required to reduce manual workload, improve response time and to ensure system reliability.
• Creates and maintains documentation for all servers, applications, tools, scripts, and procedures.
• Researches new technologies and makes technology recommendations to lead HPC Systems Administrator or appropriate director.
• Creates HPC systems and application environment designs, which should include performance, fault tolerance, fail‑over and disaster recovery considerations. Makes recommendations to Lead HPC Systems Administrator or appropriate director.

Bachelor's degree in an information technology related field; OR four (4) years of experience in an information technology related field; OR an equivalent combination of relevant education and/or experience.

• Experience with administration and programming Linux computational computing clusters.
• Experience working with HPC job schedulers, Slurm scheduler preferred.
• Experience and understanding of parallel file systems is preferred.

Administrative

$65,000 - $75,000

Begin time: 8:30 AM
End time: 5:00 PM

Expanded Background Check

• Ability to work evenings and weekends.
• Ability to work flexible hours as needed.
• Travel to FIU Campus.
• Must be available 24/7 for possible emergency situations.

FIU is a State University System of Florida member, Equal Opportunity, Equal Access, and affirmative action employer for individuals with disabilities and veterans. All qualified applicants will receive consideration for employment decisions, programs, and events without regard to race, color, religion, sex, age, national origin, disability, or protected veteran status. For inquiries regarding non-discrimination, contact FIU's Office of Civil Rights at  or email ocr.

Should you need an ADA accommodation to participate in a University event, program, or activity or need to request materials in an accessible format, please contact FIU's Office of Civil Rights (OCR) at  or accommodations. All requests for ADA accommodation or accessible materials for this event must be submitted to OCR at least seven (7) business days prior to the event or at the earliest possible opportunity.