Apply your Linux administration skills to help turbocharge research at the University of Colorado! The CU-Boulder Research Computing group (www.rc.colorado.edu) has an opening for a High-Performance Computing (HPC) System Administrator, who will implement and support large-scale computing and storage systems. This is a hands-on position that will focus on day-to-day configuration and implementation, problem solving, and providing technical assistance.

The CU Research Computing infrastructure currently includes a 16,000-core Linux-based supercomputer with almost 1 petabyte of parallel storage, several smaller compute clusters aimed at high-throughput or memory-intensive tasks, a general data storage system that will grow to several petabytes of disk and tape, and a high-speed network for high-performance applications. These resources are available to any CU faculty member or researcher.

We are happy to hear from candidates whose HPC experience may not be extensive, but who are independent learners and sincerely enthusiastic about providing CU researchers with a stable and well maintained HPC environment. Ideal candidates will be self-motivated, not easily flustered, and able to work smoothly within a team.

Job responsibilities of the HPC System Administrator will include:
> System administration of RC storage services, including hardware maintenance, file system configuration, storage server updates, and mount and export maintenance.
> Diagnosing, solving, and implementing solutions for the RC supercomputer and computational clusters; may include hardware repairs, operating system configuration, system software updates, and procedure automation. Assisting with network hardware and network service maintenance and configuration. Responding to end-user queries.
> Proactive daily monitoring and health checks of the research computing infrastructure. Using and extending existing Nagios infrastructure, and developing additional monitoring scripts and/or platforms.
>Testing and tuning storage and computational systems to increase performance and reliability.
>Maintaining and/or creating documentation in support of the research computing infrastructure.

Required Qualifications:
> Bachelor's Degree in Computer Science or Computer Engineering or related field. A combination of education and relevant experience as described below may be substituted for the degree on a year for year basis.
> 1 year of enterprise-level experience in a combination of the following:
>Building, configuration and administration of Linux or Unix computer systems.
>Diagnosing system and application software problems.
>Scripting in Perl, bash or Python.

Required Competencies:
>Exceptional ability to work effectively both within a team and also independently, as circumstances warrant.

Desired qualifications:
> Demonstrated experience in system and related network administration of complex computer systems, specifically Linux systems and preferably Linux clusters.
> Demonstrated experience with a parallel file system, e.g. GPFS or Lustre.
> Knowledge of or experience in networking systems and software including DNS, LDAP, and TCP/IP.
> Familiarity with configuration management tools (i.e. Cfengine, subversion, RCS).
> Familiarity with ticket tracking systems.
> Demonstrated ability to follow through with assignments and commitments in a timely and professional manner.
> Demonstrated experience working in an environment with rapidly changing job priorities.
> Knowledge of or experience administering computer security software and hardware requirements.
> Knowledge of Linux kernel internals.

If you are interested in this position or would like to learn more, please visit: www.jobsatcu.com, posting # 819797. Applications submitted by the end of the day on Nov. 25 will receive full consideration.
CU-Boulder is an EEO/Affirmative Action Employer.