University of Rochester System Administrator Lead - 234417 in Rochester, New York
System Administrator Lead Job ID 234417Location Central Administration Full/Part Time Full-Time Favorite Job Regular/Temporary Regular Opening
Full Time 40 hours Grade 055 CIRCSchedule
8 AM-5 PMResponsibilities
The Center for Integrated Research Computing (CIRC) is seeking a full-time experienced System Administrator Lead to support a Linux-based research computing environment. The candidate should have 10 or more years of experience as a Linux Systems Administrator, preferably in a high performance computing (HPC) environment. Reporting to the Assistant Director, the position requires the candidate to configure, operate, and maintain the technical computing, network, cloud-based, and storage resources for CIRC. The candidate must have the ability to do the following tasks: perform system builds, deploy system software, perform software integrations, work with vendor technical resources, and monitor server, network, and storage performance. Familiarity with a parallel storage systems (GPFS, Lustre, BeeGFS, etc.) is highly desired. Similar familiarity with on-premise and cloud-based virtual machine environments (VMWare, AWS, OpenStack, Azure, etc.) is also highly desirable. The candidate must be able to meet with members of the research community, gather requirements, and suggest possible solutions and/or assist in using CIRC resources. The ability to evaluate new storage architectures, systems, and software tools to determine the best techniques for achieving performance and to identify future acquisition objectives is required. The successful candidate must be able to respond to emergency situations involving system troubleshooting, debugging, root cause analysis, and monitoring triggers. Creating and maintaining documentation aligned with CIRC’s workflow tracking is also critical. Candidates must be able to work in a team environment and be able to adapt and deploy new technologies, as appropriate. This position will require some oversight of junior staff members to achieve project based objectives.
The Center for Integrated Research Computing supports the University of Rochester’s research mission by providing technical computing services to the institution’s research community. These services include high performance computing, visualization, large, fast, reliable storage systems and hundreds of software packages used by researchers to analyze data. CIRC also provides assistance with using these tools via workshops, classes, tutorials and consulting services. This position is important due to the indirect and direct support provided to the researchers in achieving and maintaining a high level of satisfaction by the research community.
Under direction of the Assistant Director and with latitude for the exercise of independent judgment and initiative:
20% - Acts as a project manager for a major operating system while maintaining multiple operating and other system support programs with a constant awareness of projects and deadlines and communicating progress to leadership to determine effectiveness. May require oversight of junior staff members
20% - Will assume responsibility for applications dealing with the overall operating system or with complex sub-systems of the operating system, such as parallel file systems, file management routines, copper and fiber networks and advanced mathematical/scientific software packages
20% - Responsible for supporting the administration of the on-premise and cloud-based virtual machine environment for CIRC’s research community
20% - Responsible for defining logic, codes, tests and debugs programs; determines the root cause of computer operation malfunctions and provides solutions along with steps to mitigate future risk of repeat issues
10% - Keeps abreast of trends as they relate to the technical computing field, with particular emphasis on high performance computing environments, by self-study, attending job related seminars, courses or conferences which enable personal development and strengthens the user service function. Must work effectively in a team environment and help disseminate newly acquired knowledge, while maintaining a high level of satisfaction regarding end user interaction and team cohesiveness
10% - Performs other related duties, including presentation of seminars, supporting courses and instruction of technical computing related services in support of the research community, as required
REQUIRED EDUCATION AND EXPERIENCE:
Bachelor's degree in related discipline such as Computer Science, Business, Statistics, Science or Engineering and at least 10 years of related experience or an equivalent combination of education and experience
RedHat Enterprise Linux/CentOS expertise
Linux systems administration - 10+ years
Ability to install and maintain complex Linux applications (databases and other system applications)
Knowledge of Linux system security, e.g., authentication, port blocking/forwarding, firewalls, ACLs, etc.
Deep understanding of networking protocols, architecture and fundamentals
Ability to write scripts and tools for system monitoring, maintenance and automation
Proficient in one or more scripting/programming language (Perl/Python/Java/C) in order to develop specifications for extremely complex systems programming applications
Evaluates and modifies existing programs to take into account changes in systems requirements or equipment configurations
Experience with the installation and configuration of web and application servers (e.g. Apache httpd and Apache Tomcat)
Experience with storage hardware management - disk arrays, NAS systems, object based storage systems
Strong oral, written, and team communication skills, effective questioning, listening, and analytical skills
Experience with high performance computing systems, including Linux computing clusters, job resource managers and schedulers
Experience with parallel file systems, standard RAID and de-clustered RAID technologies
Knowledge of InfiniBand network technology
Proficiency with cloud based technologies like AWS, Azure, and local clouds
Experience with virtualized environments like VMWare, QEMU, OpenStack, etc.
Demonstrated proficiency in identifying the requirements for creating system and user documentation
Experience leading a team of junior system administrators in best practices and work related efficiencies
Capable of taking new ideas and technologies and providing leadership with a plan for successful implementation from start to finish
Experience in working in a research computing environment
Knowledge of scientific and technical computing applications
Center for Integrated Research Computing (CIRC)
The University of Rochester established the Center for Integrated Research Computing (CIRC) to provide researchers across its Medical Center and River Campus with resources necessary to utilize computing and data analytics technology in all areas of academic scholarship. CIRC currently maintains systems with an aggregated computational performance of approximately 1500 teraFLOPS, 5.2 petabytes of disk storage, and a variety of scientific software applications and tools, supporting over 1,000 users from diverse departments and research centers. Resources that ensure access to the technology and knowledge for effective computational and analytics research include: computer systems, software, storage, expert full-time staff, student assistants, information sharing, collaboration tools, and an education and training program. CIRC supports multiple sponsored research projects currently totaling $64 million per annum from federal and state agencies. Monthly research symposia and regular workshops help investigators use computational and data science technologies and allow over 200 faculty research groups across the University of Rochester to participate in discussions and collaborative opportunities centered on the application of computing technology to research. From novice users, unfamiliar with the command line environment of a Linux cluster, to research associates who have compilation and optimization questions about custom-developed software, CIRC is uniquely positioned to collaborate with faculty and students in computational research design and implementation, software implementation and lifecycle management, application porting and tuning, data visualization and analysis techniques, and the development and proliferation of new computational and data science technologies and methods.How To Apply
All applicants must apply online.
EOE Minorities/Females/Protected Veterans/Disabled