System Administrator - Marseille, France - ATG Europe

ATG Europe

Entreprise vérifiée

Marseille, France

il y a 1 semaine

Posté par:

Sophie Dupont

beBee Recruiter

Description

Maintain and evolve HPC system deployment solution (RHN Satellite/Spacewalk); update of kickstarts/activation keys/distributions/configuration files/post install-scripts;

Maintain and evolve the calculation nodes operating systems; CentOS 5 and higher;
Maintain and evolve the HPC job scheduler and the calculation queues associated;
Maintain and evolve the HPC authentication appliance by creating and maintaining users and groups databases (winbind/LDPA);
Perform regular security and errata update on the HPC;
Monitor all HPC systems using Nagios and Splunk;
Assist in review of calculation code with scientists to implement them on the HPC;
License and Hardware management;
Keep documentation up to date;
Followup of the installation of the new nodes using latest CentOS released;
Improvement and mandatory changes for the HPC deployment solution;
Improvement and mandatory changes for the HPC job scheduler and the jobs related.
Post Secondary Diploma or Bachelor Degree in Computer Science or Engineering or another domain relevant for the profile;
At least 5 years of relevant working experience, of which 3 years in a similar role;
Previous experience with HPC (High Performance Computer) support services, in particular: Support services in HPC administration including job scheduling (Torque/Maui, SGE), node provisioning (xCAT), HPC code compilation & libraries management (MPI, OpenMPI, modules), configuration management (Puppet), compilers (Intel Composer, PGI), parallel storage (Lustre, GlusterFS) and low latency network (Infiniband);
MSCA Certification is advantageous;
Fluency in English, both written and spoken;
Eligibility to work and live in the EU.