Junior HPC Systems Engineer: Learn to Run Large Clusters

Parallel Works; Chicago (IL); Hybrid; USD 70,000 - 100,000; Full time

Benefits offered by this job

Medical coverage

Vision coverage

Dental coverage

401(k) with company match

Short term disability

Generous paid vacation

Generous sick time

Job summary

Parallel Works is hiring a Junior HPC Systems Engineer to learn supercomputing operations on production systems. The role starts with monitoring, node health, and account and allocation work, and moves into cluster builds and escalations.

The systems are hybrid: on-premises clusters the customer owns, accredited Government cloud regions, and commercial GPU providers, often in the same day. We are looking for strong Linux fundamentals and interest in how large systems behave.

Qualifications

• 2+ years of hands-on Linux administration (RHEL/ Rocky/ Alma, Debian/Ubuntu).
• Understanding HPC fundamentals: batch scheduling, shared filesystems, MPI job launch.
• Bash and Python scripting for operational work.
• Practical networking: DNS, routing, firewalls, SSH keys, bastion access.
• Git and ticket-driven workflow; clear written communication.
• Interest in on-premises estate: bare metal, out-of-band consoles, site networking.
• US citizenship and eligibility for Secret clearance; active clearance helpful.

Responsibilities

• Monitor cluster health, node state, queue behavior, and alerting; take initial action on node failures and file system alerts.
• Manage accounts and Slurm allocations; keep users and groups consistent across venues.
• Oversee node lifecycle: health checks, draining, returning nodes, escalation paths.
• Extend Ansible playbooks and operational scripts; automate repetitive steps.
• Patch and harden systems; document baselines; accompany security review.
• Maintain runbooks and participate in on-call rotation after training.

Job description

Parallel Works is hiring a Junior HPC Systems Engineer to learn supercomputing operations on production systems. The role starts with monitoring, node health, and account and allocation work, and moves into cluster builds and escalations.

The systems are hybrid: on-premises clusters the customer owns, accredited Government cloud regions, and commercial GPU providers, often in the same day. We are looking for strong Linux fundamentals and interest in how large systems behave.