Postdoctoral Fellow in Machine Learning and Multimodal AI — Brigham and Women’s Hospital / Harvard Medical School

Description

Offer Description: The Kovacheva Lab at Brigham and Women’s Hospital and Harvard Medical School in Boston is recruiting a postdoctoral fellow in AI and machine learning . We are looking for a strong, independent computational researcher who wants to develop original machine learning methods, shape their research direction, and collaborate closely with clinicians on meaningful healthcare problems . Research opportunities Our research integrates physiological signals, medical imaging, clinical text, and electronic health records, with applications in maternal and perioperative medicine. Potential directions include: Physiological time-series modeling: ECG, PPG, and hemodynamic waveforms, including temporal patterns and irregularly sampled clinical data. Computer vision and representation learning: Ultrasound and other medical imaging modalities. Multimodal learning: Integrating physiological signals, images, clinical text, and structured electronic health records. Robust and trustworthy ML: Model development, rigorous validation, generalizability, and translation to clinical prediction tasks. Specific projects will be developed jointly around the fellow's methodological strengths and research interests, aligned with the lab's funded priorities. What makes this opportunity distinctive? Our lab combines close clinical collaboration, access to large-scale real-world clinical datasets, and established research infrastructure . We developed MERLIN, a scalable platform for clinical data processing and reproducible dataset generation, providing a foundation for research with complex, heterogeneous healthcare data. The fellow will have opportunities to formulate original research questions, lead projects and publications, mentor junior researchers, and develop an independent research direction with clinical and computational mentorship. Who should apply? We welcome candidates with: A PhD in computer science, engineering, statistics, applied mathematics, physics, or a related quantitative discipline, completed before the appointment begins. Strong Python programming skills and hands-on experience in machine learning or deep learning. Demonstrated ability to conduct original research, including rigorous experimental design, model evaluation, and scientific publication. Expertise in at least one relevant area, such as time-series modeling, computer vision, representation learning, NLP, or multimodal AI. Prior clinical or healthcare experience is not required, and expertise across every modality is not expected. We particularly value scientific curiosity, creativity, and the ability to critically evaluate research findings. The position is based in Boston, USA , with a hybrid working arrangement that includes on-site participation. International applicants are welcome. How to apply Please submit your CV, a brief cover letter describing your research interests, key scientific contributions, and fit for the position, and links to one or two representative publications or preprints. Include your anticipated availability to start. Applications will be reviewed on a rolling basis. Requirements: Research Field Computer science » Informatics Education Level PhD or equivalent Skills/Qualifications PhD in computer science, engineering, statistics, applied mathematics, physics, or a related quantitative discipline, completed before the appointment begins. Strong Python programming skills and hands-on experience developing and evaluating machine learning or deep learning models. Research expertise in at least one relevant area, such as physiological time-series analysis, signal processing, computer vision, representation learning, natural language processing, or multimodal learning. Evidence of original scientific contributions and the ability to lead a research project from question formulation through rigorous analysis and scientific communication. Strong communication skills, a collaborative approach, and an interest in interdisciplinary research.

Sectors

Source

Source: euraxess.ec.europa.eu