Apply on Employer Site

Calspan · 6 hours ago

Server Administrator

US-NY-Buffalo

Full-time

Onsite

Mid, Senior Level

$80K/yr - $110K/yr

3+ years exp

Calspan is seeking a highly skilled Server Administrator to manage core infrastructure and High Performance Computing (HPC) environments. This role is responsible for the stability of Windows Servers and Red Hat Enterprise Linux clusters, as well as supporting critical engineering simulation software.

AerospaceAutomotiveIndustrialManufacturingTest and Measurement

No H1B

Responsibilities

HPC Cluster Administration: Deploy, configure, and manage Linux-based HPC clusters. Monitor node health, job queues, and system performance to ensure maximum throughput for engineering simulations

Application Support: Troubleshoot and optimize engineering simulation software, specifically Ansys Fluent and Star-CCM+. Resolve issues related to MPI libraries, parallel processing, and solver convergence errors caused by infrastructure constraints

License Management: Manage floating license servers (e.g., FlexNet/FlexLM) for engineering applications to ensure availability and compliance

Job Scheduling: Administer workload managers/job schedulers (e.g., Slurm, PBS, or LSF) to prioritize and distribute engineering jobs effectively

RHEL Administration: Expert-level management of Red Hat Enterprise Linux. Handle kickstart deployments, satellite management (if applicable), kernel tuning, and security hardening

Virtualization: Manage the hypervisor layer (e.g., VMware vSphere, HyperV). Handle VM provisioning, resource pooling (CPU/RAM), and performance tuning for virtualized engineering workloads

Identity & Access Management: Administer user access in Active Directory/Entra ID, ensuring seamless authentication for both Windows and Linux/HPC environments (via LDAP/SSSD)

HPE Storage Administration: Manage the complete lifecycle of HPE storage infrastructure, specifically HPE Nimble arrays

Performance Tuning: Optimize storage protocols (NFS/iSCSI) to handle the high I/O throughput required by HPC simulations

Capacity Planning: Utilize HPE InfoSight to monitor trends and forecast storage needs for large engineering datasets

Backups & DR: Maintain robust backup strategies and Disaster Recovery plans for critical engineering data

Infrastructure-as-Code: Write and maintain scripts using Python, Bash, or PowerShell to automate cluster node provisioning and system maintenance

Configuration Management: Use tools like Ansible to enforce consistent configurations across the HPC nodes and general server estate

Qualification

Red Hat Enterprise LinuxHPC Cluster AdministrationAnsys FluentHPE Nimble StoragePythonBashJob SchedulersInfrastructure-as-CodePerformance TuningCapacity Planning