Job Summary

The University Research Computing Facility (URCF) is a centrally reporting core facility that provides access to high-performance computing hardware and software resources for research computing. The URCF occupies a 1,600 sq. ft., 0.6 MW, climate-controlled server room that hosts the NSF-Drexel funded Picotte shared HPC cluster, which consists of 4,224 compute cores and 48 Nvidia Tesla V100 GPUs along with a high-capacity storage system. The Director of High Performance Computing (HPC) is responsible for the design, installation, monitoring and maintenance of hardware, software and networking equipment for HPC systems in the URCF. The position reports to the Operations Director of Research Core Facilities (part of the Office of Research & Innovation). The Director of High-Performance Computing will also work closely with the Faculty Director of the URCF, who leads a Faculty Advisory Committee charged with helping the facility develop and meet its strategic, financial and operational goals. URCF financial administration is provided by the Office of Research & Innovation.

Essential Functions

• Technology Management and System Administration
  • The Director of High Performance Computing will install/monitor/maintain computing hardware/networking for the various HPC systems in the URCF.
  • Manage user accounts, allocations of hours and storage, and batch queuing shared HPC systems.
  • Manage and maintain software and operating systems on shared HPC systems.
  • Develop and manage all documentation relevant to the shared HPC systems.
  • Develop and manage software for monitoring and reporting URCF activities and usage.
  • Interface with hardware vendors for specifying and purchasing hardware.

• User Education and Assistance
  • Develop and/or maintain user-facing documentation and real-time system status information.
  • Provide consultation services on the use of HPC, and the use of various programming languages and analytical software. Provide effective user and first-line technical support for the HPC research community helping with scientific computer language compilers and libraries, pre and post processing data analysis.
  • Provide advisory support to faculty/users for grant and manuscript submissions.

• URCF Development and Administration
  • Meet regularly with the Operations Director for Research Core Facilities and URCF Faculty Director to discuss current needs, new technologies, educational and outreach activities, career development, personnel management, and operational issues.
  • Direct involvement in the planning, design and implementation of the next shared HPC systems at Drexel. This includes serving as Principal Investigator or Co-investigator on any NSF or NIH proposal for shared computing equipment.
  • Work with Office of Research and Innovation business staff to develop and implement accounting practices for annual rates calculation, billing and purchasing.
  • Work with Office of Research and Innovation business staff to ensure core compliance with all applicable regulations.
  • Contribute to the development of a core business plan for the URCF that includes sustainability and optimization of existing services and identifies priorities and opportunities for future instrumentation and services.
  • Contribute to the development of metrics to evaluate the impact of the URCF on the University Research and Academic missions.
  • Contribute to the preparation of an annual report summarizing the activities, developments and impact of the URCF.
  • Manage the facility staff, including co-op employees and work study participants.

Required Qualifications

• Master’s Degree or Equivalent in Computational Research
• 4 years of relevant experience
• Considerable knowledge of principles of computing and/or communications networks, and characteristics of computing hardware and software used in distributed environments.
• Strong oral and written communication skills.
• Ability to assemble complex HPC architectures.
• Ability to assimilate, retain, and utilize technical and applications-oriented information.
• Ability to establish and maintain effective working relationships.
• Ability to work with considerable independence and initiative.
• Knowledge of safety and security precautions appropriate to work performed

Preferred Qualifications

• PhD. with a research focus on HPC.
• Troubleshooting HPC hardware failures: memory, hard drives, motherboards, TCP/IP networking, InfiniBand fabrics.
• Working with OpenSUSE, CentOS, RHEL, Fedora, Ubuntu, and other Linux distributions.
• Experience using and administering the SLURM job scheduler.
• Administering academic scientific software (MATLAB, etc.).
• Working with Fortran, C/C++, python, and bash.
• Basic Wiki management and webpage development.
• Working with storage/RAID systems, network files systems, parallel file systems.
• Configuring network switches, routers, VPN’s and network installs.
• Working with software/hardware vendors.
• Handling and managing access to protected health information.
• Answering end-user questions about running software in an HPC environment.

Physical Demands

• Typically sitting at a desk/table
• Typically standing/walking
• Lifting demands 25lbs

• Typically bending, crouching, stooping

Location

Hybrid/Flexible Arrangement, Philadelphia, PA

Additional Information

This position is classified as Exempt with a salary grade of O. For more information regarding Drexel’s Professional Staff salary structure, https://drexel.edu/hr/career/ducomp/salstructure/

Please review the Benefits Brochure for some information on our benefits offerings.

Special Instructions to the Applicant

Please make sure you upload your CV/resume and cover letter when submitting your application.

Review of applicants will begin once a suitable candidate pool is identified.