Machine Learning Researcher

ph3Postdoctoral Position in Multimodal Generative AI for Biomedical Imaging and Genetics /h3 pFor the bItalian Institute of Technology (IIT) /b, we are looking for a PhD holder with advanced expertise in Machine Learning and Computer Vision to join the bArtificial Intelligence for Good (AIGO) /b research group and work on multimodal and generative models for biomedical imaging, with the goal of predicting genetic information and clinical risk from medical images. /p pKeep reading if you: /p ulliHold a PhD in Artificial Intelligence, Machine Learning, Computer Vision, Computer Science, Engineering, Physics, Mathematics, or a related field /liliHave a strong research background in Machine Learning, Deep Learning and Computer Vision, preferably applied to medical/biomedical imaging or other scientific domains /liliHave worked with multimodal models or approaches integrating images with structured, biological, clinical or genetic data /liliHave published research in Machine Learning, Deep Learning and/or Computer Vision journals and conferences /li /ul pThis position may not be for you if you: /p ulliAre looking for a permanent position /liliCome from a genetics or genomics background but have never worked with Deep Learning models /liliHave mainly used existing Machine Learning or Deep Learning models as ready-made tools, without being directly involved in their development, training or adaptation to complex scientific problems /li /ul h3Who you will be working with /h3 pThe selected candidate will join the bItalian Institute of Technology (IIT) /b, a research institution established to promote technological development and advanced scientific training in Italy. /p pThe position is within the bArtificial Intelligence for Good (AIGO) /b research group, led by bProf. Vittorio Murino /b, an internationally recognised researcher in Artificial Intelligence. /p pThe group currently includes approximately 25 PhD students, postdoctoral researchers and research scientists. Its research focuses on learning from imperfect data, particularly in multimodal settings, including unsupervised, semi-supervised and self-supervised learning, as well as learning from weakly labelled, noisy, imbalanced or biased data. Other research areas include domain adaptation and generalisation, few-shot and zero-shot learning, continual learning and learning from biased data. /p pThe group also works on generative models, with particular attention to recent multimodal foundation models, including bLarge Language Models (LLMs) /b and bVision-Language Models (VLMs) /b. bFurther research focuses on lightweight Machine Learning approaches aimed at developing energy-efficient AI technologies, including applications on edge devices such as robots. /b /p pAIGO also develops AI methods that incorporate ethical considerations, privacy, fairness and robustness from the ground up, with the goal of developing Deep Learning techniques that are explainable, reliable and transparent. Its main application areas include biomedicine, biology, neuroscience and healthcare. /p pAIGO collaborates with several international universities and research centres, including close collaborations with the Universities of Genoa and Verona. /p h3The project /h3 pThe position is funded by bDompé Farmaceutici /b within the project b“AI Driven Prediction of Glaucoma Linked Genetic Variants from OCT Retinal Imaging.” /b /p pThe project aims to explore whether bretinal OCT images and heterogeneous biomedical data can be used to predict genetic factors and the risk of developing glaucoma. /b /p pThe research will focus on developing models capable of learning phenotypic representations from images that can serve as predictive indicators of underlying genotypic factors. /p pThe project therefore aims to move beyond traditional approaches based primarily on statistical association analysis, leveraging the ability of Deep Learning to learn from high-dimensional imaging data together with contextual and multimodal information. /p h3What you will work on /h3 pYou will not simply apply existing models to a biomedical dataset. Instead, you will contribute, as part of the research team, to the bdesign, development and validation of new methodological solutions /b. /p pIn collaboration with the AIGO team, you will: /p ulliDesign and investigate Machine Learning and Deep Learning models capable of linking medical imaging data to biological, genotypic or genetic risk factors /liliWork on multimodal and generative models, representation learning and data-driven approaches applied to images and heterogeneous biomedical data /liliAddress challenges related to limited supervision, data heterogeneity and the availability of multiple sources of information /liliConduct research both independently and in collaboration with other AIGO researchers /liliSupervise and support PhD students involved in the project /liliContribute to publications for high-level international scientific journals and conferences /liliSupport the preparation of research proposals for national, international and industry-funded projects /li /ul h3Who we are looking for /h3 pApplications will be considered only from candidates holding a bPhD in a field relevant to the project /b, such as Artificial Intelligence, Machine Learning, Computer Vision, Computer Science, Engineering, Physics, Mathematics or a related discipline. /p pA documented scientific publication record relevant to the position is also required. /p pEssential technical expertise /p ulliDocumented experience in bMachine Learning, Deep Learning and Computer Vision /b, preferably applied to medical or biomedical imaging, with particular attention to multimodal learning /liliIn-depth knowledge of bgenerative models /b, such as GANs, diffusion models, encoder-decoder architectures or optimal transport-based models /liliExperience using generative models for brepresentation learning, data modelling or complex scientific problems /b /liliStrong knowledge of modern Deep Learning approaches, including bTransformers and Graph Neural Networks (GNNs) /b /liliExcellent programming skills, preferably in bPython /b, and hands-on experience with Deep Learning frameworks such as bPyTorch /b (preferred), TensorFlow or equivalent /liliStrong publication record in recognised scientific journals and conferences /liliExcellent written and spoken English /li /ul pExperience in bmedical or biomedical imaging is highly valued /b. Candidates from other scientific domains may also be considered, provided they have a strong methodological background in analysing complex images and data and are motivated to apply their expertise to biomedical research. /p pPreferred, but not essential /p ulliExperience developing multimodal approaches integrating images, structured data, metadata or other sources of information /liliExperience with domain adaptation, few-shot learning, zero-shot learning, self-supervised learning, model debiasing or continual learning /liliExperience analysing biomedical or biological data, such as medical images, imaging-derived features, structured metadata or population-level measurements /liliApplication of Deep Learning techniques to scientific domains such as chemistry, materials science, drug discovery, physics or scientific imaging /liliExperience fine-tuning or deploying foundation models, including Large Language Models and Vision-Language Models /liliHands-on experience with HPC infrastructures /li /ul pPersonal skills /p pWe are looking for researchers who share AIGO's ambition to develop AI methods capable of addressing complex scientific problems at the intersection of bbiomedical imaging, genetic data and health /b. /p pThe ideal candidate will be comfortable working in multidisciplinary and multicultural environments, combining the ability to work independently with active contribution to a collaborative research team. /p pWe are also looking for the mindset typical of research: a strong drive towards innovation and continuous learning, together with creativity, a results-oriented approach and the ability to manage time and priorities effectively. /p h3What we offer /h3 pThe successful candidate will be offered a b12-month postdoctoral contract, with the possibility of renewal /b, with a bgross annual salary in the €32K–€40K range /b, depending on skills and experience. /p pDepending on the role and contractual arrangement, private health insurance may also be provided. /p pThe position offers bflexible working hours and occasional remote working when needed /b. Candidates must nevertheless be willing to brelocate to Genoa or the surrounding area /b. /p pCandidates moving to Italy from abroad, as well as Italian citizens who have continuously carried out scientific research abroad and meet the applicable requirements, bmay be eligible for significant tax benefits under the Italian tax regime for researchers returning or relocating to Italy /b. /p pIIT also provides dedicated support for administrative and bureaucratic matters, including relocation and entrepreneurship-related needs. /p pBeyond the salary /p pBy joining AIGO, you will have the opportunity to work on an bopen scientific problem at the intersection of Artificial Intelligence, biomedical imaging and genetics /b, contributing not only to the application of existing models but also to their methodological development. /p /p #J-18808-Ljbffr