Head of The Centre for High Performance Computing

Your tasks
Position Overview
Work Environment
The Max Planck Institute of Geoanthropology (MPI-GEA) was founded in the summer of 2022; it is a dynamically growing, highly-interdisciplinary and international research institution. The research focuses on modeling and analyzing the interrelationships between biophysical and human-made systems, looking from the deep past to the future to examine how humanity has driven the emergence of the Anthropocene - the period in which human activities began significantly impacting our planet’s climate and ecosystems - and identifying potential intervention points towards a more sustainable future.
The transdisciplinary research at MPI-GEA will combine research areas represented by all three scientific sections of the Max Planck Society (MPG): Biology & Medicine; Chemistry, Physics and Technology; and Human Sciences. Corresponding inter
- and transdisciplinary research projects concern, for example, planetary urbanization, the global food system, and global material, energy, and information flows.
Your tasks
- Establish, lead and develop the HPC Centre at MPI-GEA
- Oversee the design, installation, and maintenance of the Institute’s HPC systems and associated components
- Together with the HPC Centre staff, promote and ensure stability and consistency of the HPC system, including compute nodes, storage systems, and networking
- Coordinate and communicate with Max Planck Compute centers and represents the MPI-GEA to committees working with HPC
- Technical, operational, and infrastructural analysis of scientific requirements and research activity
- Ensure data integrity and security, backup procedures, and disaster recovery plans are in place and routinely tested
- Monitor system performance and implement necessary tuning adjustments to achieve optimal performance and effective use of resources and energy
- Maintain a secure HPC environment by setting and enforcing policies and procedures
- Supervise, train, and support HPC staff, post-docs, and PhD students on best data management and computation practices
- Develop and maintain documentation, including user manuals, system architecture, and troubleshooting guides
- Stay current with HPC trends, technologies, including artificial intelligence, and best practices to recommend and implement improvements and support the scientific development of new modeling approaches.

**Profile**:
**Skills Required**:

- Profound knowledge of HPC cluster architectures, storage solutions, and networking
- Familiarity with common HPC tools, libraries, and job schedulers (e.g., Slurm, Torque, PBS)
- Ability to provide technical guidance and mentorship
- Knowledge of security practices relevant to HPC environments
- Problem-solving skills, especially in diagnosing and resolving system-level issues
- Experience in leading, managing and motivating teams
- Excellent collaboration and communication skills in English, both written and verbal (willingness to learn German would be highly appreciated in case of another native language)
- Ability to provide technical guidance and mentorship
- Knowledge of security practices relevant to HPC environments.

**Education & Certifications**:

- Master’s degree in Computer Science, Engineering, or a related field
- Relevant certifications in HPC, Linux, or related technologies can be advantageous.

**Experience**:

- Minimum of 5-7 years of experience managing and supporting HPC clusters, with a demonstrated history of increasing responsibility
- Proven experience working in a scientific research environment, preferably collaborating with researchers, post-docs, and students
- A track record of successfully implementing and maintaining HPC systems, with a focus on optimization, scalability, and security
- Experience in training and mentoring technical staff and users.

**Desirable Attributes**:

- An understanding of the specific and individual computational challenges faced in scientific research and willingness to address these challenges adequately
- Experience with cloud-based HPC solutions or hybrid HPC models
- Prior exposure to machine learning or AI workloads on HPC systems

**Offer**:
We offer you a full-time or part-time (at least 30 hours/week) employment contract and an attractive salary in accordance with TVöD Bund in line with the specific job description and your personal requirements up to EG 14, as well as an additional annual bonus. You are entitled to a 30 days' holiday and time off on 24th and 31st December. We also offer attractive and family-friendly flexitime and home office arrangements. A company pension scheme (VBL), an employer subsidy for a job ticket, the opportunity for further training, and language and health courses round off our offer.
The Max Planck Society has set itself to employ more people with disabilities. Applications from people with disabilities are expressly encouraged.
We are committed to promoting diversity and actively combating prejudice based on gender, nationa