|
Job Description
|
Summary: Responsibilities include system administration and user support of large production scientific computing platforms consisting of shared or distributed memory multi-processors clusters. Provide technical leadership in problem solving and in-depth consulting for problems involving the system operation. Duties will include working as part of a team responsible for administration and management of clustered Linux systems, including analysis, design, and implementation of modifications to the system software in order to improve system performance, correct errors, or fulfill specific needs. These needs may involve the design and development of software providing new features to the end user. Team members participate in planning new hardware acquisitions, developing operating policy, interacting with vendors, educating customers, and communicating and collaborating with other CCN groups, teams, and projects and other supercomputer sites. Non-standard working hours and on-call support of systems will be required. Applicants are requested to describe in their applications/resumes specific job experience and knowledge as it directly relates to the required skills noted below.
Required Skills: Demonstrated experience in Linux system administration. Familiarity with Linux system internals and kernel design. Demonstrated programming experience in one or more Linux shell languages (e.g., sh, tcsh, zsh, ksh) or PERL. Demonstrated ability to follow through with assignments and commitments in a timely and professional manner. Demonstrated effective oral and written communication skills. Demonstrated experience working effectively in a team environment. This position requires a Q access authorization. Applicants must have the ability to obtain a Q clearance, which normally requires U.S. citizenship.
Desired Skills: Demonstrated experience in using 1) Cfengine, 2) SystemImager, or 3) RedHat Package Management (RPM) for administering Linux clusters. Demonstrated experience configuring, installing, or maintaining any of the following for high performance computing Linux clusters: 1) High-performance networking (i.e., InfiniBand, LANai); 2) Parallel message passing technology; 3) Global parallel file systems (e.g., Lustre, Panasas); 4) Clustermatic technologies (www.clustermatic.org). Proven ability to interact with the Linux kernel community. Experience with or training in software engineering, regression testing of software, configuration control, or risk management. Experience with resource management or utilization software for job scheduling of user programs. Demonstrated experience in system administration of high-performance computing Linux clusters consisting of 32 nodes or more. Demonstrated experience in programming with C. (NOTE: Applicants may be asked to provide examples of programs they have written.) Demonstrated experience working in an environment with rapidly changing job priorities. Knowledge of or experience administering computer security software such as Kerberos, SSHv2, or authentication technologies (e.g., CRYPTOcard, PAM). Active DOE Q Clearance desired. Must be US Citizen
Education: Bachelor of Science degree in computer science, computer engineering, or other related technical degree.
|
Please describe the job you are offering. Do not include your company name or contact information here. Applicants respond by submitting their resumes. |