System administrator IT - Befattningen är under tillsättning eller redan tillsatt, och det är inte längre möjligt att lämna in en ansökan

HPC2N is one of Sweden's leading national supercomputing centers. One of our colleagues is on leave so we are now looking for a substitute. We seek a dedicated systems engineer that wants to work with cutting edge technology, help us with our cloud environment, and make HPC and AI available to a broader community of researchers.

Deadline for applications is December 4, 2023.

High Performance Computing Center North (HPC2N) is one of Sweden's leading supercomputing centers, and member of NAISS (National Academic Infrastructure for Supercomputing in Sweden). HPC2N is hosted by Umeå University and has a partnership with the Institute of Space Physics, Luleå University, Mid Sweden University, the Swedish University of Agricultural Sciences, and Umeå University.

HPC2N is operating high-performance parallel computer systems and networks, large-scale disk and tape storage systems. All levels of user support are offered, to make sure researchers can make use of our resources in the best possible way.

HPC2N’s main compute resource, Kebnekaise, is currently undergoing a process of renovation, with new CPU:s and GPU:s to meet the need of our users. At the same time, we are striving to make Kebnekaise more user-friendly to new users of HPC and AI.

For more information about HPC2N: http://www.hpc2n.umu.se

Description of work tasks
The work tasks include operation, system maintenance and further development of HPC2N's computer resources, including high-performance parallel computer systems and networks, large-scale disk and tape storage systems. Furthermore, work with HPC2N's and other regions' cloud resources which are part of the Swedish Science Cloud. The work involves participation in local, national, and international projects, as well as assisting other Swedish HPC centers.

The tasks include operation and maintenance of hardware and software, monitoring, troubleshooting, user support, etc., of federated cloud systems in an OpenStack-based environment. Installation and troubleshooting of hardware and software make up a large part of the tasks. The work also includes the development of new tools and services. Evaluation of new technology is an integral part of the work. User support is an important part of the work. Much of the work is performed in an agile manner in a DevOps-inspired form. Tasks may also include project management and coordination of work in various projects and activities at local and national level.

We primarily work with Linux (Ubuntu and RedHat), but other operating systems also occur.

Keywords in what we do are: Linux (Ubuntu, RedHat and derivatives thereof), OpenStack, CEPH, Spark, Apptainer, Docker, Kubernetes, Galera Cluster, Software Defined Networking (e.g., VXLAN), Infiniband, parallel file systems (Lustre), queue system (Slurm), security systems (Kerberos, SSH), Ansible, Puppet, Easybuild, Git, a number of different programming languages (e.g., C, C++, Java, various scripting languages such as Ruby, Python, Perl, and various shells) as well as other cloud, grid and web technologies.

Participation in national and international projects occurs.

Qualifications
University education in technical computer science or experience and competence that can be considered equivalent.

Knowledge and experience of scientific computing and cloud environments is a requirement. This includes documented experience in several of the following areas:

• Operation of larger distributed and parallel systems in a Linux environment (Ubuntu, RedHat and/or derivatives thereof)
• Virtualization and container environments in Linux
• Installation and administration of OpenStack in federated and complex environments
• Installation of hardware and software
• Experience with CEPH and other object-based storage systems
• Scripting languages: shell script, Perl and Python
• Operation and administration of networks and network equipment
• Automation of recurring tasks
• Supervision and monitoring of complex heterogeneous computer environments
• User support and advanced user support

The main part of the work will take place in an international environment, which is why it is a requirement to be able to express oneself well in English both in speech and writing.

High demands are placed on being able to independently plan one's own and others' work, as well as to organize, document and follow up the work, but also on cooperation skills and the ability to communicate with colleagues and users.

Certifications in Linux distributions (e.g., RedHat), cloud environments and high-performance networks (e.g., Infiniband) are advantageous.

Application
Your application must be written in Swedish or English and should contain:

• A cover letter, max 2 A4 pages, that motivates your interest in this position and that explains why you are the person to be hired. The letter should also include a discussion of your experience and your view of system administration.
• A curriculum vitae
• Contact information of at least two reference persons (no reference letters are required)
• Documentation of formal qualifications (diplomas, course transcripts, course certificates, etc.)
• Documentation of former positions, relevant experiences and other qualifications
• References (links) to publicly available development projects and repositories you have been part of.

Should the submitted material be in a language different from Swedish or English, an English translation must be included too.

Terms of employment
This is a temporary employment full-time for 12 month. Start date as per agreement.

Contact
More information about the position can be given by HPC2N director Paolo Bientinesi, tel +46 720 856 180, pauldj@cs.umu.se