High Performance Computing (HPC) Specialist

A day in the life of an HPC specialist? This is what it looks like:

It was a Thursday morning when Noah, a High Performance Computing Specialist within the IT for Research (ITvO) team at Vrije Universiteit Amsterdam, parked their bike in the underground bike parking next to the New University Building on De Boelelaan. A new workday was about to begin, filled with challenges, teamwork, and complex problems.

08:30 – A Calm Start

Noah began the workday with a cup of coffee while their computer booted up. The first task of the day was to check the status of the BAZIS HPC cluster. This powerful computing cluster is used by researchers from various faculties for intensive scientific calculations, simulations, and data analyses. With deep knowledge of Linux and experience in managing clusters, this was a routine task for Noah, but one that was crucial for ensuring a stable work environment.

They logged into the head node and ran a few shell scripts that automatically checked the status of all nodes within the cluster. Everything seemed to be in order, but Noah noticed that one of the compute nodes was performing slower than usual. An internal analysis began: checking the logs and using their knowledge of monitoring tools to investigate the issue further.

09:15 – Problem Analysis and Solution

After digging deeper, Noah discovered that one of the nodes was overloaded by a user running a very intensive simulation. This caused bottlenecks for other tasks running simultaneously. With insight and experience in performance analysis and optimization, Noah quickly realized that the limits on concurrent processes needed to be adjusted to alleviate the system's load.

Noah adjusted the settings in Slurm, a widely used resource manager on HPC clusters, and informed the researcher involved about the changes. They also explained how the task could be executed more efficiently in the future by utilizing parallelization techniques such as MPI and OpenMP, and perhaps even CUDA if the computational work warranted it.

10:30 – Collaborating with Researchers

The remaining part of the morning was dedicated to meetings with researchers. The research department ‘Theoretical Chemistry’ was working on Molecular Dynamics simulations and needed advice on optimizing their code for the GPU accelerators on the cluster. Noah had extensive experience with GPU programming, particularly with NVIDIA CUDA and to a lesser extent with OpenCL, and knew exactly how to assist them.

During the meeting, the research team presented the study's design while Noah took notes. After their presentation, Noah provided detailed advice on how to rewrite their code to fully leverage the parallel processing power of the GPUs. Noah also explained how to containerize their work with Docker or Singularity, making it easier to potentially move their simulations to Snellius, the Dutch national supercomputer, for even larger-scale execution if needed.

12:00 – Lunch and Informal Conversations

During lunch, Noah met with some colleagues in the cafeteria. It was a mix of IT Specialists from the ITvO team and researchers from the Computational Medicinal Chemistry and Biomolecular Simulation groups who use the BAZIS cluster for molecular dynamics and drug design. The conversation quickly turned to the latest developments in supercomputing and the use of cloud offloading for HPC tasks. Noah had some experience with HPC in the cloud and shared insights on how utilizing cloud resources could help the university scale their computing capacity, especially during peak periods.

13:00 – Project Work and Documentation

After lunch, Noah returned to the desk and continued working on a project. Noah was responsible for expanding the storage capacity of the HPC cluster. The university had recently invested in a new data storage platform with a new parallel filesystem solution. The team leader had assigned Noah to oversee the implementation on the HPC. Noah collaborated with the ITvO storage team to integrate the new storage and ensure it worked seamlessly with the existing infrastructure.

Noah documented every detail of the process. It was important to record everything carefully so that colleagues and future HPC specialists could easily access this information. Technical documentation was an essential part of Noah's work, and while it could be time-consuming, Noah understood how important it was for the team's success.

15:30 – An Unexpected Challenge

While wrapping up the documentation, Noah received an urgent email from a Bioinformatics researcher. There was a problem with a large dataset that couldn't be correctly placed on the cluster. Such issues were not uncommon, and Noah's analytical skills were invaluable in diagnosing the cause.

After a thorough analysis, Noah discovered that the problem was related to a faulty NFS connection between the compute nodes and the storage space. With knowledge of various storage solutions, Noah quickly devised a solution. Noah adjusted some NFS parameters to prevent recurrence and ensured that the researcher could resume work without further issues.

17:00 – Wrapping Up the Day

Toward the end of the day, Noah checked the status of the cluster one last time. Everything was running smoothly, and the issues that had arisen earlier in the day were all resolved. Before leaving, Noah made a brief note for Monday's team meeting, summarizing the results of the performance analyses and the progress of the storage expansion.

With a sense of satisfaction, Noah stepped outside, ready to leave the day behind. Tomorrow would bring another day full of challenges and collaboration, something to look forward to. As an HPC Specialist at Vrije Universiteit Amsterdam, Noah knew that all efforts had a direct impact on the success of scientific research, which gave daily fulfilment.

• Background
• Bachelor's or master's degree in computer science, mathematics, physics, data science, engineering, or a related field.
• Academic working/thinking level or candidates with several years of work experience in the field instead of the above are also very welcome to apply.

Hardware, Storage, and Networking

• Knowledge of high-speed network architectures (such as Infiniband (preferred)) and storage technologies like parallel file systems (such as BeeGFS, Lustre, GPFS).
• Understanding of storage solutions (SAN, DAS storage, etc.) and fine-tuning them.

Cluster Management

• Experience with setting up (preferred) / managing HPC clusters (knowledge of resource managers such as Slurm, PBS, etc.).
• Experience with monitoring and optimizing cluster performance.

Operating Systems & Software

• In-depth knowledge of Linux/Unix systems, particularly in the context of server management.
• Experience with shell scripting for task automation and management.
• Knowledge and experience with parallel and distributed programming using MPI, OpenMP, CUDA, etc.
• Familiarity with containerization and virtualization (such as Singularity).

A challenging position in a socially engaged organisation. At VU Amsterdam, you contribute to education, research and service for a better world. And that is valuable. So in return for your efforts, we offer you:

• a salary of minimum € 3.345,00 (Scale 10) and maximum € 5.278,00 (Scale 10) gross per month, on a full-time basis. This is based on UFO profile ICT Manager 2. The exact salary depends on your education and experience.
• a position for at least 0.8 FTE. Your employment contract will initially last 1 year.

We also offer you attractive fringe benefits and regulations. Some examples:

• A full-time 38-hour working week comes with a holiday leave entitlement of 232 hours per year. If you choose to work 40 hours, you have 96 extra holiday leave hours on an annual basis. For part-timers, this is calculated pro rata.
• 8% holiday allowance and 8.3% end-of-year bonus
• hybrid working enables a good work-life balance
• space for personal development
• possibility to save holiday hours, for sabbatical leave

About the department, institute, project
Provide more information about the department, institute, project, etc. Keep it brief. This is not a required section. If you do not use this text block, then delete it including the title.

Information Technology
We at Information Technology (IT) have the responsibility of ensuring a worry-free digital environment for researchers, students and staff. We facilitate teaching and research with IT resources, advise on IT products and services, and keep the application landscape for work and study up-to-date. We ensure that the university’s IT facilities are up and running 24/7.

At the same time, we focus on the future of digital – everything from the smart campus and cyber security to open science and artificial intelligence. Along with the faculties and service departments, we look ahead to ask: how can we prepare now for tomorrow’s questions? Together we look for better and better ways to support the university’s ambitions in the areas of education, research and valorisation.

Are you interested in joining IT? Working in IT means operating on a complex, often hectic and challenging playing field, where both development and management demand your attention. We give you plenty of scope to show initiative and take responsibility. Learning from one another is key, while remaining focused on results. In Information Technology, you will join over 200 colleagues spread over 4 departments.

Vrije Universiteit Amsterdam
Vrije Universiteit Amsterdam stands for values-driven education and research. We are open-minded experts with the ability to think freely. - a broader mind. Maintaining an entrepreneurial perspective and concentrating on diversity, significance and humanity, we work on sustainable solutions with social impact. By joining forces, across the boundaries of disciplines, we work towards a better world for people and planet. Together we create a safe and respectful working and study climate, and an inspiring environment for education and research. Learn more about our codes of conduct

We are located on one physical campus, in the heart of Amsterdam's Zuidas business district, with excellent location and accessibility. Over 6,150 staff work at the VU and over 31,000 students attend academic education.

Diversity
Diversity is the driving force of the VU. The VU wants to be accessible and receptive to diversity in disciplines, cultures, ideas, nationalities, beliefs, preferences and worldviews. We believe that trust, respect, interest and differences lead to new insights and innovation, to sharpness and clarity, to excellence and a broader understanding.

We stand for an inclusive community and believe that diversity and internationalisation contribute to the quality of education, research and our services.

Therefore, we are always searching for people whose backgrounds and experience contribute to the diversity of the VU community.