Assistant Director of Research Computing

$104,000 - $117,000/Yr

University of Maryland - Baltimore, MD

Full-time - Mid Level

Baltimore, MD

51-100 employees

Educational Services

About the position

The Assistant Director of Research Computing at UMBC is a key role within the Division of Information Technology, responsible for overseeing the operations of the research computing infrastructure. This position involves guiding the future of high-performance computing and ensuring that researchers effectively utilize computing resources to enhance their work. The role includes collaboration with various stakeholders, training users, and developing solutions to support research initiatives.

Responsibilities

• Support the wide range of disciplines UMBC's RC/CI Offerings.
• Collaborate with researchers and colleagues at other research institutions in applying information technology to research problems.
• Work with researchers from a variety of disciplines to understand their applications and application performance.
• Assist researchers to leverage the parallel CPU and GPU architectures of computing resources supported by UMBC DoIT RC Group.
• Coordinate with cluster administrators concerning the needs of the UMBC research computing community and facilitate user-friendly access to those resources.
• Respond to reported problems and provide solutions.
• Provide guidance to existing and potential users on how to use the cluster for their research projects through both one-on-one consultations and training sessions.
• Facilitate and develop specific training programs aligned to UMBC's advanced cyber infrastructure resources.
• Work closely with DoIT and campus stakeholders to actively pursue infrastructure and research computing related funding opportunities and partnerships.
• Design and implement solutions to support research collaborations, including solutions involving both software and hardware components and different functional and performance requirements.
• Design and architect logical solutions to administer the HPCF and its resources.
• Build tools and support architectures used to facilitate computational workflows and organize experiments in conjunction with best practices.
• Serve as the UMBC Campus NSF Campus Champion.
• Maintain familiarity with emerging techniques and technologies in research computing.
• Participate in training, education and development activities to improve knowledge and performance and enhance professional development.
• Attend relevant academic and professional conferences.
• Perform additional duties as assigned.

Requirements

• Master's Degree preferably in Computer Science, Information Systems, or related field with at least three years experience working with HPC or parallel computing clusters or three years of experience in RC/CI administration.
• Experience with NVIDIA Bright Cluster Manager or other cluster management software.
• Experience with versioning tools such as Git or Subversion.
• Install and/or configuration of CEPH, parallel or high performance file systems.
• Slurm or other cluster computing job management experience.
• Experience supporting customer requests and working with stakeholders to gather and fulfill project requirements.
• Capable of managing time effectively, working both independently and as part of a team.
• Help develop project plans, effectively create/update issues and keep team members and management informed of changes, impediments, and updates.
• Enthusiasm for learning new skills and adapting to a dynamic environment.
• Strong interpersonal skills, enthusiasm for customer service, and the ability to work with students, staff, and faculty from diverse backgrounds.
• Excellent written and verbal communication skills.

Nice-to-haves

• Master's or coursework equivalent in a traditionally non-computing, but STEM-related field (e.g., Applied Mathematics, Engineering, Biology, Geology, Chemistry, Physics, etc).
• Five or more years of experience in RC/CI administration.
• HPC knowledge around cluster builds, software, parallel computing, workload management, and cluster management.
• Three years of advanced programming in Python and/or C/C++.
• Familiarity with Linux & modern computing tools (e.g., Jupyter Ecosystem, MATLAB, and/or similar).
• Familiarity with machine learning workflows/pipelines.

Benefits

• Generous Leave which includes accruing 22 Days of Annual Leave, 15 Days of Sick Leave, 15 Holidays, and 3 Personal Days.
• Tuition Remission for 8 credit hours per semester and for eligible dependents after two years of FT employment.
• Life and disability insurance.
• Retirement plans (including the choice of joining the pension plan).
• Professional development opportunities.
• Wellness opportunities.