Phd-position (M/w/d) - Computer Vision for in Situ

The multidisciplinary Institute for Advanced Simulation - Materials Data Science and Informatics (IAS-9) brings together disciplines ranging from data analysis and machine learning to materials simulation, research data management and software development under one roof. In doing so, we extract new information from simulations and experiments, identify patterns, structure, and trends in microscopy data, and ultimately improve our understanding of why materials, processes, or general systems work the way they do. In addition, we benefit from a strong connection to the Ernst-Ruska-Centre for Electron Microscopy and to the Jülich Supercomputing Center. One part of our research activity is dedicated to pushing the boundaries of materials science and electron microscopy. Our work combines cutting-edge imaging techniques with deep learning to unravel the behavior of lattice defects, specifically dislocations, in functional materials under mechanical stress. This research is essential for advancing fundamental science and ensuring the reliability of materials used in energy transition.

**Your Job**:
You will strengthen the data science and machine learning activities of the IAS-9 with exciting new topics. You will work with a multidisciplinary team of enthusiastic data scientists, software developers and domain scientists on, e.g.,
- Developing deep learning-assisted methods for in situ electron microscopy with enhanced time resolution using adaptive scanning
- Contributing to the development of self-supervised and unsupervised learning techniques for resolution enhancement, denoising, and representation learning of electron microscopy images
- Implementing supervised learning methods for the accurate detection and segmentation of dislocations in annotated electron microscopy images
- Utilizing diffusion models to generate synthetic TEM images, providing training data for segmentation, denoising and super resolution
- Collaborating on the development of domain adaptation methods for transferring learned representations to different experimental setups
- Designing and implementing active learning strategies to minimize the number of annotated images required for model training
- Working in close collaboration with the research team to enable real-time feature tracking with adaptive scanning during electron microscopy experiments
- Preparing scientific publications and participating in international conferences and workshops

**Your Profile**:
We are looking for a highly motivated colleague who is excited about new scientific endeavors with interdisciplinary approaches. For this you have:

- Practical experience in the area of data analysis, data mining and ML/DL demonstrated through, e.g., a thesis, publications in peer-reviewed journals or open source projects
- Prior experience in computer vision, image analysis, or machine learning
- Strong programming skills in Python and experience with deep learning frameworks such as TensorFlow or PyTorch
- Prior knowledge and experience in (electron) microscopy is highly desirable
- Excellent communication skills and commitment to work as part of a team

**Our Offer**:
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:

- The opportunity to conduct exciting research in an international and multidisciplinary environment with outstanding infrastructure and to strengthen your reputation in a dynamic and highly active research field
- Outstanding scientific and technical infrastructure
- The opportunity to attend national and international conferences
- Flexible working hours in a full-time position with the option of slightly reduced working hours and flexible work arrangements, e.g. working from home
- Ideal conditions for balancing work and private life, as well as a family-friendly corporate policy
- Targeted services for international employees, e.g. through our International Advisory Service
30 days of annual leave and provision for days off between public holidays and weekends (e.g. between Christmas and New Year)

To apply, please submit a complete CV, letter of motivation, university degree records and certificates.