A Postdoctoral Research Fellow position in biomedical informatics is available at Harvard Medical School to work at the intersection of advanced machine learning and large-scale biomedical data. The selected fellow will join a dynamic research group focused on several synergistic goals: generating actionable Real-World Evidence (RWE) from multi-institutional Electronic Health Records (EHR), improving the generalizability of clinical evidence across diverse populations using multi-source and multi-modal data, and accelerating drug discovery by leveraging these rich, integrated datasets. This role offers a unique opportunity to develop methodological innovations that bridge the gap between computational theory and impactful clinical application.

We are seeking a highly motivated individual with a strong statistical and machine learning background. The ideal candidate will have existing expertise in several of the following areas, aligned with our research focus: 1) Causal inference, invariant learning and representation learning; distributionally robust optimization; 2) Graph Neural Networks, Large Language Models (LLMs), and geometric deep learning; and 3) federated learning and privacy preserving computing.

Candidates must hold a Ph.D. in a quantitative field, such as statistics, biostatistics, computer science, or a related discipline. Success in this position requires strong quantitative research capabilities and demonstrated proficiency in programming, specifically in Python and R, as well as experience with modern deep learning frameworks like PyTorch or TensorFlow. In addition to technical skills, the candidate must possess excellent written and oral communication abilities to effectively disseminate research findings and collaborate within a multidisciplinary team.

Mo Moro

Information regarding postdoctoral fellow salary, which is determined by the number of years post PhD, can be found at https://postdoc.hms.harvard.edu/guidelines