PhD Position – Scalable AI and Advanced Computing Earth Ob

PhD Position – Scalable AI and Advanced Computing for Earth Observation

The operates one of the most powerful computer systems for scientific and technical applications in Europe and makes it available to scientists at Forschungszentrum Jülich, in Germany and across Europe for research purposes via an independent peer-review process. As part of this remit, the JSC carries out research and development work in the fields of technology, HPC systems, communications, highly scalable data science, mathematics and application support.

The department develops machine learning techniques and other methods and tools for the management, analysis and modelling of large-scale data, and for the integration of data and computing resources into federated HPC infrastructures. The models, tools and methods are developed in collaboration with users in selected scientific domains, tested, scaled for the pre-zettascale era and offered as generic solutions to a large number of scientific communities.

Join us now and contribute with your expertise to this interesting field.

In this position, you will join our . The lab advances interdisciplinary research and operational services by combining geoscience and remote sensing methods with AI and advanced computing technologies for Earth observation (EO) applications, including climate science, forestry, or agriculture. Your doctoral research will investigate how AI methods and workflows can be designed and adapted to handle large, heterogeneous EO tasks efficiently and reliably.

You will develop and evaluate approaches that address the trade-offs between predictive performance, computational efficiency and scalability, using high-performance and cloud computing environments. Depending on the agreed research direction, you may also explore hybrid quantum-classical approaches. You will work closely with our researchers and international partners from academia, industry and public agencies.

• Review the scientific literature and formulate research questions at the intersection of AI, EO and advanced computing
• Develop and investigate AI methods for multisource EO data, exploring approaches such as geospatial foundation models and representation learning
• Design reproducible data and experimental workflows for model training, adaptation and evaluation on selected EO applications
• Investigate MLOps pipelines for reproducible, efficient and scalable training and inference on parallel, distributed and GPU-accelerated computing systems
• Benchmark the developed approaches against established methods, assessing predictive performance, generalisation, computational requirements and scalability
• Collaborate with domain researchers and computing specialists to validate your methods on relevant EO problems and integrate research prototypes into shared software and workflows
• Publish your findings in scientific journals and present them at international conferences, contribute to open-source research software and prepare your doctoral thesis

• An excellent master’s degree or equivalent in computer science, data science, applied mathematics, physics, scientific computing, remote sensing, geoinformatics or a related field
• A solid foundation in machine learning and relevant mathematical methods, including linear algebra, probability and optimisation
• Experience in one or more of the following areas would be advantageous: EO or geospatial data analysis, parallel or distributed computing, GPU programming, Linux and containerised environments, quantum computing, or agentic AI
• Prior industry experience, publications and open-source contributions are welcome
• Good programming skills, preferably in Python, and practical experience implementing and evaluating…