Job Title

The Probabilistic Vision Group (PVG) at McGill University and MilaQuebec Artificial Intelligence Institute, led by Prof. Tal Arbel, seeks Postdoctoral Fellows to advance causal-temporal and probabilistic modeling, 3D spatio-temporal generative models, and multimodal foundation modelsincluding vision-language MLLMs and agentic AI frameworksfor longitudinal MRI and clinical data. Fellows will help build next-generation models for neurological diseases (e.g., Multiple Sclerosis) and cancers, applying these modeling advances to patient-level outcome prediction, treatment-response modelling, and the discovery of image-based predictive markers. The position includes exclusive access to a proprietary multi-center MS clinical-trial MRI dataset (10k+ patients; longitudinal multi-sequence MRI with manual lesion labels, treatment codes, and progression outcomes) and high-end compute (hundreds of NVIDIA H100 GPUs) via Mila and the Digital Research Alliance of Canada, and involves active collaborations with Stanford, Oxford, Google Research, and Meta. Responsibilities: The development of probabilistic deep learning models that capture the temporal evolution of complex chronic diseases from sequential medical images (plus clinical information) to predict plausible outcomes for patients on and off treatments. Driving innovative research in causal representation learning, inference, and discovery; advance explainable models that enable discovery of image-based markers predictive of future disease evolution; and build fair, robust models for reliable predictions, along with uncertainty estimates. Advancing multimodal foundation models (images, text, clinical data), temporal 3D generative models for longitudinal MRI, and MLLMs/agentic-AI frameworks leveraging reinforcement learning for complex clinical-reasoning tasks. In addition, Postdoctoral Fellows will: Collaborate with clinicians and researchers at the Montreal Neurological Institute and the Goodman Cancer Research Centre, with McGill and Mila teams, and with academic/industry partners (e.g. Stanford, Oxford, Google Research, Meta) Mentor and supervise graduate students. Qualifications: PhD in machine learning, with experience in applications in computer vision or medical image analysis. Strong publication record in top venues (e.g., CVPR, MIDL, MICCAI, IPMI, PAMI, TMI, MIA, NeurIPS, ICML). Strong mathematical skills; programming skills and ML/DL experience (e.g., PyTorch/TensorFlow). Additional Skills (assets): Experience with temporal/longitudinal MRI and temporal 3D generative models. Background in uncertainty, explainability, fairness, and robustness for trustworthy predictions. Familiarity with multimodal foundation models, vision-language / MLLMs, agentic-AI, and reinforcement learning for clinical reasoning. Annual Compensation: $80,000 (plus applicable benefits) Hours per Week: 35 (Full time) Position Start Date: December 15, 2025 Position End Date: December 14, 2026 Deadline to apply: November 1, 2025 McGill University hires on the basis of merit and is strongly committed to equity and diversity within its community. We welcome applications from racialized persons/visible minorities, women, Indigenous persons, persons with disabilities, ethnic minorities, and persons of minority sexual orientations and gender identities, as well as from all qualified candidates with the skills and knowledge to productively engage with diverse communities. McGill implements an employment equity program and encourages members of designated groups to self-identify. Persons with disabilities who anticipate needing accommodations for any part of the application process may contact, in confidence, . #J-18808-Ljbffr