Hpc Tl
2 weeks ago
JOB SUMMARY
Supporting and implementation of HPC clusters & storage systems (via onsite/telephone/VPN) managed services and using industry standard methodologies. Working with HPC software stacks including Linux operating systems, MPI's, schedulers, and low latency interconnects such as InfiniBand. Familiarity with software compilers, programming, Linux administration, and networking are required. Troubleshooting, debugging.
PRIMARY RESPONSIBILITIES
Should be able to demonstrate skills on User Administration, File System Administration, Mail Server, Web Server, DHCP, NFS, NIS,LDAP, Proxy, SAMBA,NTP, DNS,Corosync, Pacemaker, Heartbeat, DRBD, RCS, IPTABLES and other relevant domain knowledge.
Should be proficient in Cluster toolkit (GANANA,IBM,PCM,ROCKS,xCAT & MM Clusters)
Parallel file systems (Lustre, GPFS, GlusterFS).
Scheduler (Open grid engine, PBS pro,Torque, LSF), Compiler(GNU & Intel), MPI(Open MPI,Intel MPI & MPICH2) and Cluster monitoring tools (Ganglia)
Should be able to handle escalations raised by L2/L3 Engineers.
Plan new implementation/Installation of HPC Cluster.
Providing customers with remote/telephonic support.
Work on in-house developed software.
Design and validate proposed HPC solution of presales/sales team.
Schedule preventive maintenance of clusters installed in various locations.
Taking feedback of incident handling.
