Rachel Buckley

Postdoctoral opportunity in machine learning , deep learning , and multimodal prediction for Alzheimer’s disease risk at Mass General Brigham , within the Buckley Lab and the Harvard Aging Brain Study Data & Informatics Team . This role is designed for a highly quantitative researcher who wants to apply advanced computational methods to rich longitudinal biomedical data. The project focuses on large-scale data science and clinically translational research in Alzheimer’s disease, including deep phenotyping, cross-cohort data integration, disease heterogeneity, and modeling of expected vs. observed disease trajectories. Research topics mentioned include multimodal prediction models, artificial neural networks, survival/time-to-event modeling, clustering, latent subgroup discovery, interpretable machine learning, model validation, generalizability, domain adaptation, uncertainty quantification, and handling missingness and cohort heterogeneity. The work uses harmonized multi-cohort data from more than 10 international aging and AD cohorts, including clinical, cognitive, neuroimaging, blood biomarker, vascular, and demographic data. Ideal applicants have a PhD in computer science, bioinformatics, applied mathematics, biostatistics, computational neuroscience, engineering, or a related quantitative field. Strong programming and scientific writing skills are expected. Experience with Alzheimer’s disease or neurology is helpful but not required. The post emphasizes teamwork, curiosity, and strong technical expertise. The environment includes close collaboration with Dr. Timothy Hohman and Dr. Michael Donohue, plus interaction with the broader Mass General Brigham and Harvard communities and other international collaborators. To apply, send a CV and a 1-page cover letter describing your technical skills, career goals, and fit with the position. No deadline or funding amount is specified in the post.