Postdoc Funke Group

Vedi l’offerta su Go Lavoro: golavoro.it/annuncio-lavoro/806bqb

ppbPostdoc | Human Technopole, Milan /b /p pbApplication closing date: /b /p pJoin a place where ambitious science thrives Human Technopole (Milan) is a rapidly expanding life science institute where international researchers and cutting-edge technologies converge to accelerate biomedical discovery. Our mission is to transform bold scientific ideas into advances that improve human health. /p pIn this context, the Funke lab develops machine learning methods to accelerate scientific discovery with a focus on microscopy image analysis. Specifically, we are interested in the development of new methods to identify structures of interest in large datasets (detection, segmentation, and tracking), the creation of explainable AI methods to interrogate scientific datasets, and the design and implementation of mechanistic models of biological processes that work together with contemporary machine learning methods. /p pMany life science projects involve the acquisition of time series microscopy data to visualize the dynamics that underline cell proliferation and cell fate decisions. To analyze those datasets and gain novel insights, cells need to be reliably tracked over long periods of time; including the detection of cell division events to create comprehensive lineage trees. Although cell tracking using deep learning methods has been shown to deliver excellent results on selected datasets, experimentalists still struggle to track cells automatically on new datasets: the diversity of possible live-cell datasets makes it hard for a given method to generalize due to differences in fluorescent labeling, resolution, model organism, or exact imaging modality to name a few. No method exists as of now that can reliably handle all of those different conditions. /p pWe are looking for an ambitious Postdoc who will lead our efforts on the design, implementation, and training of active learning strategies to fine-tune a pre-trained cell tracking network.



Instead of training a generalist model for all possible cases (which is near impossible), we will instead focus on developing learning methods that can adapt to a new dataset using only very few, carefully selected human annotated samples. We will achieve this by developing an active learning framework, i.e., a deep learning system that actively asks a user for feedback in situations where the method is unsure what the correct answer is. To that end, we will make use of contemporary probabilistic models that are able to communicate their uncertainty about a given decision. /p pPractically, we will embed this network in the Motile Tracker ( an established GUI for cell tracking. /p h3Your mission /h3 ul liLead the development of an active learning framework for cell tracking. /li liGuide the development on real biomedical datasets. /li liPublish your results in conference and journal publications, together with high-quality, open-sourced, and well-documented software tools. /li liInitiate collaborations, proactively identify impactful use cases, and mentor junior researchers. /li /ul h3Grow Your Skills /h3 pThe Human Technopole is a unique environment at the intersection of many disciplines of the life sciences. In the Funke lab, you will have the opportunity to apply and grow your skills by /p ul liLeading interdisciplinary research projects in collaboration with experimental labs. /li liBeing closely involved in the experimental design, data generation process, and analysis. /li liWriting efficient,



reusable, and elegant code that can be used by others to build on top of. /li liMentoring junior researchers and communicating your results amongst peers. /li /ul pAdditionally, the Human Technopole supports career development through training, mentoring and dedicated learning opportunities. /p h3Essential /h3 h3What you'll bring /h3 ul liA Ph.D. in Computer Science, Physics, Engineering, Biology, or related fields, either completed or nearing completion. /li liExperience with machine learning. /li liExperience with scientific python packages. /li liA track record of impactful scientific contributions (papers, scientific software, high ranking in scientific competitions, or other significant research outputs). /li /ul h3Preferred /h3 ul liStrong track record of machine learning in the life sciences. /li liExperience working with cell tracking. /li liExperience working with probabilistic models. /li liExperience with active learning. /li /ul h3Organizational and Social Skills /h3 ul liAbility to initiate, lead, and sustain scientific collaborations. /li liExcellent communication and mentoring abilities. /li /ul h3At HT, your discoveries contribute to a global effort to improve human health. /h3 h3Why Human Technopole /h3 pHT offers an international and dynamic workplace, competitive welfare provisions, flexible working policies and relocation support. Researchers moving to Italy may agevolazioni from attractive tax benefits. We promote work-life balance and provide parental support initiatives. /p pThis is a 4-year contract offered under CCNL Chimico Farmaceutico, Level B2 /p pSalary: up to € 43.000,00 depending on the candidate' seniority. /p pThe position is based in Milan, Italy, within our vibrant international campus. /p pWe strongly encourage applications from candidates belonging to protected categories (L. 68/99). /p /p #J-18808-Ljbffr

Vedi l’offerta su Go Lavoro: golavoro.it/annuncio-lavoro/806bqb