The System Administrator for the Homewood High Performance Cluster (HHPC) manages a research computing cluster, which contains over 3,000 processor cores and is connected to a petabyte of storage that serves the HPC and data intensive science needs of many researchers across the Johns Hopkins University. The System Administrator oversees systems management for the group's fileservers, cluster login nodes, and associated switching fabrics and networks, and implements and manages the queuing system that balances usage among groups.
Essential Duties & Responsibilities:
Systems Engineering and Oversight
Design, organize, test and implement cutting-edge hardware designs
Document systems so that users can easily find useful information and other IT staff can perform routine tasks and provide backup.
Provides stable solutions for HHPC use
Oversee maintenance of HHPC community's technical infrastructure
Maintain HHPC and Related clusters
Plans and makes purchases to meet the needs of the HHPC community.
Maintain job scheduling and storage allocation systems and policies in accordance with the HHPC Steering Committee to ensure fair allocation of shared resources.
Maintain extensive monitoring systems to facilitate quick, proactive responses to routine failures, and to provide comprehensive performance data logging.
May provide general system administration backup for other facilities or research groups.
Ensures solutions released to the community are stable and usable.
Ensures resources meet the community's needs and are highly available to the group with limited interruption.
Optimizes clusters frequently to meet the needs of the community and are highly available with limited interruption.
Effectively meets the community's infrastructure needs so they are highly available with limited interruption.
Makes purchases and purchase requests on time and in accordance with departmental and university policy and procedure.
Project Management and Outreach
Understands HPC technical needs. Work closely with the facility's faculty steering committee to shape policies, and ensure that these policies are successfully implemented.
Conceive, initiate, define, plan, organize and execute project plans
Develop close ties with participating faculty and their research groups in order to maintain awareness of their computing needs. Facilitate community building among the facility's users to encourage sharing of solutions.
Learn from previous experiences when developing new projects.
Work closely with the facility's faculty steering committee to shape policies, and ensure that these policies are successfully implemented.
Create and maintain a stable, secure operating system and software environment, which continues
Create and maintain a stable, secure operating system and software environment, which continues to meet users' evolving research needs.
Plan the retirement of aging systems.
Develop custom tools where necessary, and contribute useful creations back to open source development efforts where appropriate.
Research new technologies that could be beneficial to HPC.
Tests and vets new technology in support of HPC efforts
Works with vendors to procure prototypes and demo units
Be involved with purchasing of additions to existing clusters. Develop custom tools where necessary, and contribute useful creations back to open source development efforts where appropriate.
Continuously evaluate new tools and technologies for use in existing and future clusters.
Attend department and University-sponsored training to increase knowledge, improve skills, and learn new skills. May substitute University training for supervisor approved commercial job related course offerings.
Internal and External Contacts
List only those contacts required to perform the major activities of this job, and the typical purpose (Exchange information, Advise/Consult, Negotiate/Influence) of the contact.
This position may interact with an array of departmental and central administrative offices, faculty, staff, researchers, and students, and with numerous external vendors for the purpose of accomplishing HPC technology goals. Works routinely with University faculty, administrators, students, and researchers. Collaborates regularly with professional colleagues from the central IT@JH organization,and from other academic departments.
Bachelor's degree. Five years related experience. Additional education may substitute for required experience and additional related experience may substitute for required education, to the extent permitted by the JHU equivalency formula. Master's degree preferred. Formal training in computational science or engineering a big plus.
Minimum 5 years' experience managing Linux Servers.
Experience as a high-level Linux Systems Administrator.
Experience managing mission critical services in a 24x7x365 environment
Johns Hopkins University remains committed to its founding principle, that education for all students should be grounded in exploration and discovery. Hopkins students are challenged not just to learn but also to advance learning itself. Critical thinking, problem solving, creativity, and entrepreneurship are all encouraged and nourished in this unique educational environment. After more than 130... years, Johns Hopkins remains a world leader in both teaching and research. Faculty members and their research colleagues at the university's Applied Physics Laboratory have each year since 1979 won Johns Hopkins more federal research and development funding than any other university. The university has nine academic divisions and campuses throughout the Baltimore-Washington area. The Krieger School of Arts and Sciences, the Whiting School of Engineering, the School of Education and the Carey Business School are based at the Homewood campus in northern Baltimore. The schools of Medicine, Public Health, and Nursing share a campus in east Baltimore with The Johns Hopkins Hospital. The Peabody Institute, a leading professional school of music, is located on Mount Vernon Place in downtown Baltimore. The Paul H. Nitze School of Advanced International Studies is located in Washington's Dupont Circle area.