PhD Position in AI with HPC – Advancing Earth Observation through Foundation Models

21. April 2024


Conducting research for a changing society: This is what drives us at Forschungs­zentrum Jülich. As a member of the Helm­holtz Asso­ciation, we aim to tackle the grand societal challenges of our time and conduct research into the possi­bilities of a digitized society, a climate-friendly energy system, and a resource-efficient economy. Work together with around 7,400 employees in one of Europe’s biggest research centers and help us to shape change!

Do you have a master’s degree in science, technology, engineering, or math? Have you applied AI techniques, preferably using self-supervised learning? Then it is time to broaden your views! Our Simulation Data Lab “AI and Machine Learning for Remote Sensing” is seeking to hire PhD students interested in tailoring self-supervised learning for applications in Earth observation. We identify challenging datasets, formulate novel research questions, train large-scale models, and strive to expand the limits of what is achievable with AI and supercomputing. For our work, we have access to large HPC systems and are interested in exploring how large amounts of unlabeled data, combined with extensive computational resources, can be leveraged for exciting real-world use cases involving satellite data and other modalities.

We are offering a

PhD Position in AI with HPC – Advancing Earth Observation through Foundation Models

You will join the Simulation and Data Lab “AI and Machine Learning for Remote Sensing”, which aims to enhance visibility in interdisciplinary research between applications from remote sensing and large-scale AI with high-performance and innovative computing. You will conduct independent research on self-supervised learning, focusing on applications in satellite remote sensing, but also considering the potential to apply these methods to different domains. Specifically, you will:

  • Develop, implement, and refine Machine Learning (ML) techniques for self-supervised Deep Learning (DL) for scientific and large-scale datasets
  • Implement parallel ML training on the High Performance Computers, including JUPITER, Europe’s first exascale computer
  • Prepare, process, and publish datasets and benchmarks for self-supervised learning in science
  • Engage in national and international ML / DL communities, most importantly the Helmholtz Foundation Model Initiative
  • Present research results at scientific meetings, conferences, and as scientific papers
  • Contribute to educational events, such as hackathons, data challenges, and courses
  • Excellent master’s degree in computer science, science, engineering, or in a similar field
  • Strong software engineering and programming skills
  • Broad interest in scientific topics
  • Very good knowledge and experience in applied ML
  • Self-motivated personality with the ability to work within a multidisciplinary team environment on challenging problems
  • Very good command of written and spoken English
  • Practical experience with ML / DL workflows and common software libraries
  • Your experience should be documented in research papers and open-source code projects

We work on the very latest issues that impact our society and are offering you the chance to actively help in shaping the change! We offer ideal conditions for you to complete your doctoral degree:

  • You will be employed as a doctoral student at the Jülich Supercomputing Centre and enrolled at the University of Iceland, greatly benefiting from holding a dual affiliation; your workplace will be in Jülich with occasional visits to Iceland
  • Work on frontiers of scientific and technological challenges with access to cutting-edge and unique supercomputing systems including the upcoming first exascale computer in Europe (JUPITER)
  • The opportunity to attend national and international conferences
  • Close support and mentoring from your team leader on a weekly basis
  • Further development of your personal strengths, e.g. through an extensive range of training courses; a structured program of continuing education and networking opportunities specifically for doctoral researchers via JuDocS, the Jülich Center for Doctoral Researchers and Supervisors:
  • Extensive company health management
  • Ideal conditions for balancing work and private life as well as a family-friendly corporate policy
  • Flexible working hours and flexible work (location) arrangements, e.g. remote work
  • 30 days of annual leave and provision for days off between public holidays and weekends (e.g. between Christmas and New Year)

In addition to exciting tasks and a collegial working environment, we offer you much more:

The position is for a fixed term of three years. Pay will be in line with 75% of pay group 13 of the Collective Agreement for the Public Service (TVöD-Bund) and additionally 60% of a monthly salary as special payment (“Christmas bonus”). Further information on doctoral degrees at Forschungszentrum Jülich including our other locations is available at