Hpc Engineer

• Design, deploy and configure HPC Clusters including compute, storage and networking components.
• Installation requests on HPC, application upgrades, and troubleshooting processes in coordination with users, software vendors and OEM.
• Administer job schedulers (e.g., Slurm), manager user access, monitor health and troubleshoot system issues on both on-prem and Cloud.
• Optimize HPC workloads, tune resource utilization and benchmark system performance.
• Install and maintain HPC hardware, software stacks, compliers, libraries (e.g., MPI, OPENMP) and custom tools. Configure VM, Storage and servers on cloud.
• Assist users in optimizing and running applications on the cluster & cloud, including guidance. Ensure System stability through regular updates, proactive monitoring and software/hardware troubleshooting.

Responsibilities

• Supervise day-to-day support operations for HPC and Cloud team by supporting ticket SLA adherence.
• Manage support ticket systems, primarily using internal IT tools.
• Ensure timely resolution of user issues related to CAE applications in HPC & Cloud.
• Plan, schedule, and oversee application upgrades and installations.
• Collaborate with internal teams and external vendors to ensure seamless issue resolution.
• Generate detailed performance reports monthly, analysing key trends and areas for improvement.

Technical Skills:

• Operating Systems: Expertise in Linux (RHEL CentOS, Ubuntu)
• HPC Tools and Frameworks:
• 1. Job Schedulers: Slurm, PBS & Sync-HPC
• 2. Parallel Programming: MPI, OPENMP, CUDA
• 3. Scripting: Python, Bash and Optionally C/C++
• Cloud: Knowledge in AWS, GCP & Azure with HPC toolkits, VM & Object storage creation.
• Networking: Knowledge of high-speed networks (InfiniBand, RDMA, Ethernet)
• Storage Systems: Experience with parallel file systems (Lustre, NFS)
• Hardware: Familiarity with HPC specific hardware wit, RAM, CPU & GPU

Certifications

• Any Cloud Solution Architect Certificate (Preferred GCP)
• RHEL Certified System Administrator (Preferred)