HPC Engineer

1. HPC Infrastructure Design & Deployment

• Design, build, and maintain HPC clusters and compute environments.

• Install and configure servers, storage systems, networking, and accelerators (GPU/FPGA).

• Plan scalable architectures for compute-intensive workloads.

2. Cluster Administration

• Manage Linux-based HPC systems.

• Monitor cluster health, node availability, hardware performance, and uptime.

• Perform patching, upgrades, and preventive maintenance.

3. Job Scheduling & Resource Management

• Configure and manage schedulers such as Slurm, PBS, LSF, Torque.

• Optimize queue policies, fair-share scheduling, and resource utilization.

• Troubleshoot failed jobs and scheduling issues.

4. Performance Optimization

• Tune CPU, memory, storage, and network performance.

• Analyze bottlenecks in parallel applications.

• Improve MPI/OpenMP/CUDA job efficiency.

5. Storage & File Systems Management

• Administer parallel/distributed file systems like Lustre, GPFS, BeeGFS, NFS.

• Ensure high-speed data access and storage reliability.

• Manage backups, quotas, and data lifecycle.

6. Networking & Interconnects

• Configure high-speed interconnects such as InfiniBand, RoCE, Ethernet.

• Diagnose latency, bandwidth, and node communication issues.