Senior HPC Systems Engineer

Parallel Works; Chicago (IL); Hybrid; USD 140,000 - 190,000; Full time

Benefits offered by this job

Medical, vision, dental coverage

401(k) with company match

Short term disability

Generous paid vacation and sick time

Job summary

Parallel Works seeks a Senior HPC Systems Engineer to build and run production Slurm clusters and oversee GPU nodes across on-prem and cloud environments. You will handle bare metal provisioning, network and firmware tasks, and ensure secure, scalable operation for defense and research programs.

The role is senior and involves triage escalations, mentoring junior engineers, and contributing to automation with Ansible or Terraform. U.S.

Qualifications

• 10+ years operating production Linux systems across multiple distributions.
• Experience with SLURM and high-throughput HPC environments.
• Experience with on-prem hardware, GPU clusters, and fabric networks.
• Proficiency in Bash and Python scripting for automation.
• Familiarity with DevOps IaC tools (Ansible, Terraform).
• Security hardening and compliance in government or enterprise settings.

Responsibilities

• Cluster operations: build and run production Slurm clusters with proper accounting and QoS.
• Hybrid federation: connect customer clusters to the control plane and align site schedulers.
• On-prem hardware: bare metal provisioning, out-of-band management, firmware, networking.
• GPU and fabric: validate GPU nodes, driver stacks, NCCL tuning, InfiniBand checks.
• Storage and automation: optimize storage throughput and develop reproducible pipelines.
• Security and escalation: STIG hardening, cryptography, Tier 3 escalations.

Skills

Production Linux systems

RHEL Rocky Alma

Debian Ubuntu Linux

kernel tuning

systemd

cgroups

NUMA

Slurm administration

InfiniBand fabric

NVIDIA GPU management

Ansible Terraform

Bash Python scripting

Tools

Prometheus

Grafana

Job description

About Parallel Works

Parallel Works builds and operates ACTIVATE, a control plane for high performance computing and AI. Our customers run large scientific and AI workloads across their own on-premises clusters, Government and commercial cloud, and commercial GPU providers, and ACTIVATE gives them one way in to all of it. The high security boundary is authorized at Impact Level 5, with FIPS validated cryptography and STIG hardening throughout.

The work reaches most fields that depend on computing at scale: weather and climate forecasting, defense and intelligence programs, aerospace and structural analysis, molecular and materials science, energy, and AI research. A quarter here can include standing up a GPU cluster for one of those communities, federating a laboratory's existing on-premises system with burst capacity it did not have before, and getting a domain code written decades ago to run on current hardware.

Customer success sets our priorities. We are a small engineering company, so engineers here work directly with the people using the systems and carry a problem from the first report through to the fix. This is what we call mission engineering: understanding what a customer is trying to accomplish and why the computing matters to it.

About the role

Parallel Works is hiring a Senior HPC Systems Engineer to build and run the clusters behind our defense and research programs. The work covers GPU node bring-up, Slurm configuration, fabric and storage troubleshooting, security hardening, and Tier 3 escalation.

The computing environments are hybrid. Some clusters are customer owned hardware on site, some run in accredited Government cloud regions, and some are dedicated GPU clusters at commercial providers. On several programs the on-premises systems carry the primary load and cloud takes the overflow. The position is senior: it handles the escalations the rest of the team cannot resolve, and it trains the junior engineers.

What you will do

• Cluster operations:build and operate production Slurm clusters. slurmctld and slurmdbd, partitions and QOS, accounts and fair share, GPU GRES, prolog and epilog, cgroup enforcement.
• Hybrid federation:connect customer owned clusters to the control plane, reconciling their site scheduler, storage, and identity source so accounts and allocations behave the same in every venue.
• On-premises hardware:bare metal provisioning, out of band management, firmware, rack networking, and fault coordination with site staff or vendors.
• GPU and fabric:validate GPU nodes before users arrive. Driver and CUDA stack, DCGM health checks, XID triage, fabric manager and NVLink checks, InfiniBand verification, NCCL tuning.
• Storage and automation:tune parallel and high throughput storage, and write the Ansible, Terraform, and image build pipelines that make a cluster reproducible.
• Security and escalation:STIG hardening, scan remediation, FIPS validated cryptography, security package artifacts, Tier 3 escalations, and a share of the on call rotation.

• 10 or more years operating production Linux systems across more than one distribution family. RHEL, Rocky, or Alma on the Government side and Debian or Ubuntu on the commercial GPU side, since those clusters usually ship Ubuntu. Kernel and network tuning, systemd, cgroups, NUMA.
• Production Slurm administration. You have configured, debugged, and upgraded a scheduler other people depended on.
• At least one parallel or high throughput filesystem in production, plus InfiniBand or RoCE fabric operations.
• NVIDIA GPU node operations at multi-node scale, including driver stack management and fault triage.
• Experience on customer owned or on-premises clusters as well as public cloud, including bare metal provisioning and out of band management.
• DevOps experience with infrastructure as code frameworks such as Ansible or Terraform.
• Proficiency with common scripting languages such as Bash and Python.
• United States citizenship and eligibility for a Secret clearance, since the work reaches export controlled Government environments. An active clearance helps. We sponsor candidates who are eligible but not currently cleared.

Preferred Qualifications

• Time at a Government supercomputing center, national laboratory, or university research computing center.
• Work with STIG, SCAP, Tenable, eMASS, or RMF, or time inside FedRAMP or Impact Level boundaries.
• Running GPU workloads on Kubernetes or OpenShift with Helm and operators, and using HPC containers such as Apptainer, Enroot, or Pyxis.
• Running PBS Pro, Slurm, and monitoring with Prometheus and Grafana, including utilization and chargeback reporting.

Benefits

• Medical, vision, and dental coverage, a 401(k) with company match, short term disability, and generous paid vacation and sick time.

Equal employment opportunity

Parallel Works is an equal opportunity employer. We consider all qualified applicants without regard to race, color, religion, sex, sexual orientation, gender identity, national origin, age, disability, protected veteran status, or any other characteristic protected by law.