Summary: This System Administrator role involves monitoring Linux systems, diagnosing performance issues, managing physical infrastructure, and implementing DCIM systems in a collaborative, fast-paced environment. Highlights: 1. Manage and monitor a large number of Linux systems and HPC infrastructure. 2. Implement and maintain Data Center Infrastructure Management (DCIM) systems. 3. Perform hands-on physical infrastructure management in a data center. Role: System Administrator (see below Job Description) Experience level: 3 to 5 years Location: DMV as there is a requirement to be on-site (Bethesda) for 5 days with occasional telework. Job Description: You will be monitoring the status of a large number of Linux systems that may be running compute jobs directly for users or supporting different parts of the HPC infrastructure. You might be diagnosing performance problems or an outage for a particular server, commissioning or decommissioning servers, running network cables, or working on documentation, both physical and electronic. This position will also take primary responsibility, under the guidance of senior staff, for implementing a Data Center Infrastructure Management (DCIM) system for Biowulf. In the course of your duties, you will need to open, follow-up on, and ultimately resolve trouble tickets with upstream vendors and with the NIH data center facilities team. These tasks will all be performed in a fast-paced and highly collaborative environment. To be successful you will need to work both independently and as a member of a team of system administrators and scientists and be able to translate broad directions into specific technical actions. Since the environment is exclusively Linux-based, you should be comfortable working in Linux (Red Hat based distributions) at least at the user level, with system administration experience preferred. However, the primary focus of this role is hands-on physical infrastructure management in the data center, including maintaining the health, connectivity, and organization of Biowulf’s server fleet. Other skill sets that are required at a high-level: • Experience writing programs or scripts in any language. • Strong familiarity with networking at the physical layer (e.g., use cases for different types of fiber and copper cables and their connectors). • Experience producing and maintaining documentation, diagrams, and rack/cable maps using tools such as Visio, LucidCharts, OmniGraffle, or similar. • Experience maintaining asset inventory in a DCIM system (e.g., NetBox) and keeping hardware records accurate over time. • Familiarity with IT asset inventory requirements (e.g., control CM-8 of NIST SP 800-53) or similar compliance frameworks. • Linux system administration knowledge (and familiarity with tools like Ansible) is a plus and will be developed further on the job. Due to the hands-on nature of this position, it requires full-time on-site with occasional telework permitted. Other skill sets that are helpful, but not required are: - Experience writing programs or scripts in any language. - Strong familiarity with networking at the physical layer (e.g., use cases for different types of fiber and copper cables and their connectors). - Experience maintaining technical charts and diagrams in PowerPoint, Visio, LucidCharts, OmniGraffle, or similar tools. - Knowledge of databases (both SQL and noSQL) and web applications. - Familiarity with inventory requirements specified in control CM-8 of NIST SP 800-53. - Experience teaching, presenting, or preparing technical reports.