As an HPC DevOps engineer you have direct influence in education and research. For example, you optimize the use of advanced technology, such as the Dutch Supercomputer Snellius. You are also at the forefront of high-performance computing and technological innovation. And all in one function. Are you the new HPC DevOps engineer from SURF?

Here you will work

SURF is the ICT cooperative of Dutch educational and research institutions. Together with them, we work on digital services and complex innovation issues to improve the quality of education and research.

You will end up in this team

The High-Performance Computing and Visualization (HPCV) team is not just any team. This team stands day after day for team cohesion, collaboration and diversity. Whoever you are and whatever cultural background you have, you are an immediate part of the team. It is hard work every day, but together with your colleagues you put your shoulders to the wheel. You reach out to your colleagues when necessary and you share your knowledge about technological innovation, whether it is need to know or nice to know.

The multicultural atmosphere is not limited to within the walls of the SURF office in Amsterdam. In addition to joint lunch walks, there are also international dinners on the menu, where colleagues share dishes from their own kitchen. Have you got the taste yet? Then we would like to add you as an HPC DevOps engineer to our team!

You are going to do this

Imagine this: in this position you work with Snellius, the Dutch National Supercomputer that enables confidential computer use for social science and economic research. Youre right on top of Snellius advanced computing infrastructure, with an impressive 240,000 cores, 640 GPUs and a dizzying peak performance of around 30 Pflops / s. As our new HPC DevOps engineer, it is up to you to manage and permanently improve the environment of Snellius as well as possible.

In concrete terms, this means that as part of the management team you are responsible for the development of the system, keeping it operational and optimizing system performance. You also play a crucial role in introducing innovative solutions you go and stand for the very best effect of Snellius.

What else you deal with

You develop and improve the ODISSEI Secure Supercomputer (OSSC). You do that in the Snellius environment. Your focus is on maintaining safety when performance is constantly optimized for the needs of the researchers.

You develop and maintain emergency services, such as OpenLDAP, that support our HPC systems.

You are working on new technologies and you are using creative solutions for our Experimental Technical Platform (ETP) team.

Together with the Operations and Innovation departments, you evaluate new hardware systems with new workflows. You are important when it comes to the continuation of those results. You also work a lot together and you constantly coordinate with consultants, DevOps engineers and other HPC DevOps engineers.

You bring this with you

As our new HPC DevOps engineer, we bring in a colleague who thinks quickly and knows what to do. With your in-depth knowledge and skills of all kinds of computer systems, you immediately shoot in the hand-sharing position, without flying out of the corner. You are analytically strong, look ahead and know what is to come. That you are orally and in writing communicative - in both Dutch and English - and have plenty of experience with various (cluster) environments, scripting languages and technologies, completes the picture.

You also have on your CV

• A bachelors or university degree in ICT technology
• Demonstrable experience in managing Linux (cluster) environments, the Bash and / or Python scripting languages and security
• Knowledge about technologies such as Slurm, IBM Spectrum Scale (GPFS), monitoring software, (Grafana, Prometheus), database software (MariaDB, Postgres), configuration management software (SaltStack, Ansible, CFEngine, Puppet) and version management software (subversion, git).

You get this from us

At SURF we are happy that you as an HPC DevOps engineer are there for us 32-40 hours a week. There may also be a lot to do with that.

You not only sign an annual contract with a view to permanent employment. We also have the following for you:

• A salary between the 3935 - EUR 6326 euro gross (based on a 40-hour working week) (wage level 2025)
• 8.33 percent holiday pay and a fixed end-of-year bonus of 8.33 percent
• 36 vacation days per year (based on a 40-hour working week)
• A good pension scheme with PNO media, where you only contribute 1/8 of the premium and SURF 7/8 part
• The ability to work hybrid. You will receive a home work allowance on your home working days
• An NS Businesscard 1st class

Two beautiful locations, in Amsterdam and Utrecht, both with good public transport facilities. Your location will be: Amsterdam. Our Amsterdam office is located at the Amsterdam Science Park, with good public transport facilities nearby.

Good to know: you need a VOG for this function.