Postdoc Machine Learning Development of Machine Learning Architectures for Data Evaluation
New membranes for the separation of substances are being developed with experiments and simulations at the Institute of Membrane Research. In past years, the evaluation of large experimental datasets by means of machine learning has become increasingly important. Within the project COMPUTING, we aim to uncover correlations between parameters and structures that remain hidden in individual experiments in order to advance the understanding of processing-structure-property-relationships of polymer membranes. For this, we will establish machine-learning-based data evaluation methods for large sets of microscopic images and fabrication parameters. Developing novel machine learning architectures and modifying published methods will be a key task in this position. The project is a collaborative effort with the Institute of Material Systems Modelling at Hereon and the HIP Service Unit ‘Applied Computer Vision Lab’ at DKFZ.
We are looking for a data scientist, computer scientist, physicist or engineer with a PhD degree as soon as possible. This position is initially limited to 21 months due to the project’s funding, with a high chance for extension in further projects. The place of work is the Helmholtz-Zentrum Hereon in Geesthacht. Part of the work can be conducted via home office.
Equality of opportunity is an important part of our personnel policy. We would therefore strongly encourage qualified women to apply for the position.
• analysis of experimental and digital processes in membrane research
• pre-processing of image data
• assembly of experimental datasets from data bases
• design and implementation of machine learning architectures for the evaluation of large scientific datasets
• combination of machine learning architectures with physico-chemical models
• validation of your results in collaboration with polymer membrane scientists
• close collaboration with other members of the COMPUTING project team
• publication and presentation of your scientific results in journals and at international conferences and workshops
- No telecommuting
- No Agencies Please
Your professional profile
- scientific university education and PhD degree in data science, computer science, physics, engineering or related disciplines
- very good coding skills in Python
- profound knowledge of Python machine learning libraries (e.g., Keras, PyTorch or TensorFlow)
- experience in Artificial Neural Networks and Kernel-Ridge-Regression / Support-Vector-Machines
- experience in statistical methods and methods of data science
- background in object-oriented programming preferable
- fluency in spoken and written English
- experience with scientific methods, project planning, publications and presentations
- German language skills are an advantage
Your personal profile
• systematic and goal-oriented way of working
• sense of responsibility and a high demand for quality in your work
• ability to tackle complex problems and to think outside the box
• joy of working in a small team and flexibility regarding the tasks involved
• proactive communication skills
• openness to an international and dynamic working environment in science
• willingness to familiarize yourself with new topics, e.g. polymer chemistry and membrane technology
About the Company
The Helmholtz-Zentrum Hereon conducts cutting-edge international research for a changing world: Around 1,100 employees contribute to the tackling of climate change, the sustainable use of the world’s coastal systems and the resource-compatible enhancement of the quality of life. From fundamental research to practical applications, the interdisciplinary research spectrum covers a unique range.
Institute of Membrane Research
The Institute of Membrane Research develops new membranes and processes for separation of substances. State-of-the-art equipment and methods for the synthesis, characterization and processing of polymers as well as membrane preparation, module development, process piloting and modelling of separation processes are the focus of research.
We offer you
• multinational work environment with ca. 1,100 colleagues from more than 50 nations
• extensive options of vocational training (i. a. expert seminars, language courses or leadership seminars)
• flexible working hours and various models to ensure the compatibility of family and career
• excellent infrastructure, including a scientific in-house library as well as modern work spaces
• remuneration according to the standards of the collective wage agreement TV-AVH including further social benefits
• free employee advice – Employee Assistance Program (EAP)
• childcare offers
• Welcome Office, guest accommodation
• PhD Buddy Program
• canteen at the Geesthacht location
Then we are looking forward to receiving your comprehensive application documents (cover letter, CV, transcripts, certificates etc.) indicating the reference number 2022/PM 5 until July 3rd, 2022.
Severely disabled persons and those equaling severely disabled persons who are equally suitable for the position will be considered preferentially within the framework of legal requirements.