The Leibniz-Institut für Analytische Wissenschaften - ISAS - e. V. is a research institute dedicated to the development and improvement of analytical methods and tools for health research and related fields. The ISAS is a member of the Leibniz Association and is publicly funded by the Federal Republic of Germany and its federal states.
A new project area in the institute is the development of advanced imaging, especially light-sheet fluorescence microscopy (LSFM), for the analysis of whole organs under physiological and pathological conditions. LSFM generates extremely large data sets. Modern machine learning and artificial intelligence (AI) provide approaches to fully exploit these data sets and translate their rich information into a better understanding of the underlying biological mechanisms. Innovative machine learning approaches promise to make hidden structures of human cognition accessible and thus guide further experimental investigation and new hypotheses. We are establishing the Analysis for Microscopy and BIOMedical images (AMBIOM) group in the department of Biospectroscopy at ISAS Dortmund.
The insistitue invites applications for a
Post-doctoral position / Scientist
Work with biomedical researchers (internal and external collaborators) to guide the study design and data collection to optimize for AI method development
Devise and carry out interdisciplinary research to develop and/or apply machine learning approaches for LSFM image analysis problems, such as segmentation, image registration, image reconstruction, image restoration, anomaly detection, etc., which are driven by real applications in life science research
Design and implement computational workflows streamlining image analysis and descriptive or inferential data analysis to make biomedical findings
Work with software engineers to (1) build the R&D methods into open-source software/packages, (2) build public AI datasets, and (3) interact with communities of practitioners to set new standards and protocols for AI based LSFM image analysis.
Report findings and methods in conference and journal papers.
For detailed requirements, please refer to https://www.isas.de/news/232021-post-doc-mwd
Develop new machine learning approaches for LSFM image analysis problems, such as segmentation, image reconstruction, image restoration, anomaly detection, etc., which are driven by real applications in life science research
Explore new theories or methodology to solve fundamental challenges in deep learning methods, such as automatically evaluating segmentation performance without ground truth, understanding generalizability and stableness of deep learning model, etc.
Work with software engineers to (1) build state-of-the-art methods or new R&D prototypes into open-source software/packages for LSFM image analysis, (2) design graphical front-end for users in biomedicine, and (3) interact with communities of practitioners to set new standards and protocols for AI based LSFM image analysis.
Report findings and methods in conference and journal papers
For detailed requirements, please refer to https://www.isas.de/news/242021-doktorand-in-mwd
Non-residents who apply for this job will receive help from the institute to find accommodation and to handle authorities. Applications from disabled applicants are welcome. ISAS supports the principle of equal opportunity for all employees and would therefore particularly encourage women to apply.
Closing date for application is 8th September 2021.
Complete applications with an extended curriculum vitae with full publication list, a cover letter, copies of your diplomas as well as your expertise and methodological competencies, names and contact information of 2 references, should be submitted as a single pdf document to firstname.lastname@example.org. Informal inquiries are welcome and can be submitted to the human resources department (email@example.com). For further information regarding the institute, please see: http://www.isas.de.
You may also contact the lab at firstname.lastname@example.org for more information or questions.