Information Technologist II

ICER's HPC systems consist of over 1000 nodes, 50,000 cores, 400 GPUs, and 9 PB of storage and supports researchers in many different scientific domains across the campus and the state.

Responsibilities

• Participate in the design, development, operation, and support of Linux-based High Performance Computing systems on campus.
• Design and support modern development and operations processes and methodologies for researchers and internal ICER needs.
• Work with other units on campus to create innovative solutions for University researchers.
• Manage complex projects that serve the entire university community as well as MSU’s external partners.
• Consult with users to ensure the best use of the University’s computational resources.
• Participate in regional and national cyber infrastructure communities.
• Include an emergency on-call support rotation (compensated) with the rest of the systems team.
• Attend weekly meetings at the East Lansing campus and perform intermittent data center work on-site.

Requirements

• Knowledge equivalent to that which normally would be acquired by completing a four-year college degree program in Computer Science, Information Systems, Business or related information technology field, with coursework in an information technology specialization related to the area of employment.
• Three to five years of related and progressively more responsible or expansive work experience in an information technology area related to the duties to be performed, such as:
  • Linux operating systems - Ubuntu, RHEL, or derivatives
  • Windows operating systems – automated provisioning, configuration, and management
  • HPCC core - Slurm, MPI, batch processing
  • Deployment methods - puppet, ansible, Chocolatey, xCAT, Lenovo Confluent
  • Scripting experience - bash, Python, Perl, Go
  • Virtualization - ESXi, kvm, XCP-NG
• Must be a U.S. citizen.

Qualifications

In addition to the core skills described above, expertise with some subset of the following technologies are desirable:

• Linux services (NFS, OpenSSH, Apache, nginx)
• Networking technologies (Ethernet and Infiniband) and hardware (Mellanox and Juniper)
• Log aggregation and monitoring (Elasticsearch, Logstash, and Kibana [ELK])
• Configuration management and automation (tools like Lenovo Confluent, xCAT, Puppet, Ansible, kickstart, Chocolatey, SNMP, and IPMI)
• Batch job queueing and scheduling systems (Slurm)
• Version control (git) and Continuous Integration (CI) or Continuous Deployment (CD)
• NIST 800-171 or 800-53, FERPA, ITAR export controls, or equivalent
• Manage Security Control Plans
• Desire for continuous learning and self-improvement

Schedule

• Hybrid role with weekly in-person meetings in East Lansing office required.
• Intermittent data center work at the East Lansing data center required.
• On-call rotation with the possible need to perform on-site data center repairs during non-business hours with short turnaround times.
• Standard 8-5 work hours.