HPC Solutions Specialist

Customer-Facing Troubleshooting (Core)

• Coordinate with other teams to support customers with installing, upgrading, and running CMG software on Linux and windows systems.
• Troubleshoot MPI-based job execution on customer clusters (scheduler, MPI runtime, nodes, networking).
• Guide customer to collect logs (scheduler output, simulator logs, MPI errors) for analyzing & reporting.
• Guide customers through structured troubleshooting when issues cannot be reproduced internally.
• Creating reports, documentation, and customer training materials for running CMG softwares over MPI.
• Building test beds to replicate user environment

Cluster & Environment Support

• Assist customers running CMG on HPC clusters (on-prem, cloud, or hybrid).
• Identify and resolve common software deployment issues such as: Software not available on all nodes, Shared path inconsistencies, Environment or shell configuration issues, Missing runtime dependencies.
• Work within customer environment constraints and policies.
• Working knowledge of HPC cluster architecture and distributed computing environments.
• Experience with HPC job schedulers such as Microsoft HPC, SLURM, and/or PBS is desirable;
• Understanding of job scheduling concepts, resource allocation, queues/partitions, job priorities and scheduling policies.
• Administer and maintain Linux-based compute infrastructure; Support server provisioning, hardware upgrades, lifecycle management, and decommissioning.
• Support Windows-based servers and workstations, ensuring system availability, and performance.
• In addition to supporting CMG’s Customers, support CMG’s internal HPC cluster and users

MPI & Networking Support

• Support common MPI implementations and validate configuration and dependencies.
• Help customers collect useful diagnostics and debug information.
• Troubleshoot node communication and networking issues affecting distributed jobs.

Scripts & Operational Improvements

• Review and improve job submission scripts for reliability.
• Provide recommended job-launch patterns.
• Document solutions and create internal knowledge base articles to improve future response time.

Licensing Support

• Verify license entitlement and investigate licensing-related runtime issues.
• Coordinate license updates or escalations when required.
• Help customer to configure license server and network according to licensing requirements.
• Configure CMG licensing features into to HPC clusters

Escalation & Cross-Team Collaboration

• Escalate complex issues to R&D with clear documentation (logs, environment details, steps taken).
• Maintain clear communication with customers during escalation.

 Note: This description reflects the general nature of the role. It’s not a complete list of responsibilities—we believe in flexibility, initiative, and growing together.