Amherst College — HPC Administrator

Amherst College

Amherst has taken a leadership role among highly selective liberal arts colleges and universities in successfully diversifying the racial, socio-economic, and geographic profile of its student body. The College is similarly committed to enriching its educational experience and its culture through the diversity of its faculty, administration and staff.

Job Description:

Amherst College invites applications for the High Performance Computing (HPC) Administrator. Given Amherst’s distinction as one of the most diverse liberal arts colleges in the country, the successful candidate will demonstrate the w ays in which they bring value to and will work towards supporting a broadly diverse community.

The HPC Administrator will work in a cross-disciplinary environment supporting the teaching and research mission at Amherst College. This position will provide leadership, expertise, and support to build and run sophisticated research-capable High Performance Computing (HPC) platforms via on-prem or co-located resources and cloud environments. The administrator will collaborate with a diverse team in the installation and maintenance of HPC systems, the overall computing environment, and complex software applications. Applicants should have knowledge of HPC systems, Linux administration, cluster management systems, open-source and proprietary software installation, scripting languages, and basic networking. Responsibilities include configuring and running new and existing HPC services and research storage systems, providing routine and on-going systems maintenance and upgrades to current HPC clusters and other computers used for research computing, securing these systems in conjunction with current data security recommendations and requirements, and monitoring and evaluating their performance and operational integrity. The HPC Administrator also works closely with Amherst’s diverse, award-winning faculty, assisting them with the development and delivery of teaching, learning, and research tools that involve or apply high performance computing.

This position requires an on-campus presence and will be part of a diverse workforce that participates in the College’s efforts to create a respectful, inclusive, and welcoming work environment.

If you have the necessary background and are looking for an environment that strives for inclusivity, that provides challenges, learning opportunities involving innovative technologies, as well as work-life balance, then you should consider this opportunity.

Summary of Duties and Responsibilities

Systems Administration.:

  • Make recommendations on changes in hardware, software and network configuration to improve delivery and availability of services.
  • Create and maintain documentation as it relates to system configuration, software configuration, and HPC processes.
  • Recommend, maintain, and implement standards and procedures for HPC administration, usage, and disaster recovery.
  • Install, monitor, maintain, support and optimize HPC systems.
  • Monitor and analyze HPC performance and availability per standard metrics, implement performance tuning, and troubleshoot a variety of moderate to complex problems.
  • Provide HPC performance statistics and reports.

Design and Implementation:

  • Implement HPC design changes for hardware, software and connectivity.
  • Analyze, evaluate, and recommend new HPC hardware, software, and connectivity products for compatibility and applicability.
  • Collaborate with a diverse set of faculty, staff and students in the identification of, design, implementation, support, and maintenance of innovative software solutions in the service of faculty and student research, teaching and learning.

Systems Outreach and Education:

  • Maintain a consistent customer-focused orientation in support of teaching, learning and research computing services delivered by HPC infrastructure.
  • Interact with staff, faculty, and students on computational needs
  • Effectively support and communicate with a diverse community of stakeholders, ensuring a culture of respect and inclusion
  • Assist system users in learning the use of new applications and services, and provide documentation on their use.
  • Assist with the training and development of HPC Technologists.

Qualifications
Required:

  • Bachelor’s degree in a technical field, or 5 years of relevant experience in lieu of a degree
  • 3-5 years experience with complex multi-system and multi-user UNIX administration, including demonstrated experience in configuration, software installation, maintenance, package management, documentation, patching, as well as backup & recovery.
  • Demonstrated experience with the use of containers and UNIX virtualization (e.g., OpenVZ, Docker, Singularity)
  • Demonstrated experience with one or more UNIX clustering technologies
  • Experience with development and support of solutions and automation via scripting (e.g., Python, Perl, Shell)
  • Commitment to supporting and contributing to a diverse and inclusive community
  • Familiarity with one or more HPC scheduling or workload management solutions (e.g., Condor, Slurm)
  • Familiarity with migrating to and managing workloads on one or more cloud platforms (e.g., AWS, Azure)
  • Exceptional ability to communicate technical concepts clearly, even to less-technical audiences.
  • Excellent organizational as well as both written and verbal communication skills.

Preferred:

  • Advanced degree in a technical field
  • Substantial experience managing and administering HPC clusters, parallel storage, and job schedulers.
  • Substantial experience with the following aspects of HPC: running scientific applications on large scale computers, optimizing and/or developing applications on UNIX-based systems, designing and developing system enhancements and software applications, queuing systems, schedulers, workload managers, and configuration management.
  • Substantial programming experience with modern languages along with development protocols, tools and utilities.
  • Experience with both traditional and GPU-based cluster environments.
  • Experience with Jupyter Notebooks, JupyterHub, and RStudio
  • Proficiency with multi-vendor hardware/software configuration.
  • Experience with problem identification/resolution, particularly in a heterogeneous environment, along with performance management/tuning and design configuration and planning.
  • Ability to provide technical leadership and management of complex, large-scale projects.
  • Substantial experience with Lustre, Hadoop, and Spark.
  • Experience in popular Artificial Intelligence frameworks as well as Matlab, Mathematica, R, and/or Python and associated libraries for machine learning and data processing.
  • Familiarity with selection, delivery, and use of cloud solutions for high performance computing workloads.

Amherst College requires all employees to be fully vaccinated for COVID-19 (medical and religious exemptions may apply).

Amherst College is pleased to provide a comprehensive, highly competitive benefits package that meets the needs of staff and faculty and their families. Benefits are an important part of our overall compensation, so it is critical that you review all of the options to ensure it meets your total compensation requirements. Click here for Benefits Information .

Interested candidates are asked to submit a resume and cover letter online at https://amherst.wd5.myworkdayjobs.com/Amherst_Jobs. Please be sure to upload all requested documents prior to clicking Submit. Applications cannot be revised once submitted. Review of applications will begin immediately and will continue until the position is filled.

To find information about job group and level (JGL) follow this link.

PI168065977

APPLY NOW: https://www.click2apply.net/ljYnWmSXEQVejiNqnC4ylq

Related: