Postdoctoral Fellowships in AI

Postdoctoral Fellowships in AI & Medical Imaging

Location:

University of Pennsylvania - Perelman School of Medicine

Open Date:
Mar 26, 2026

Faculty Mentor:
Yong Fan, PhD (Yong Fan, Ph.D.

- AIBIL)

Department:
Radiology

Funding Source: NIH

Number of positions: 3

We are recruiting three highly motivated Postdoctoral Fellows for NIH-funded positions to drive innovative research at the intersection of machine learning, medical imaging, and clinical data science. We offer a flexible, highly collaborative environment where fellows can dive deep into a specific domain or pioneer research across multiple fields.

• Neuroimaging & Predictive Modeling:
  Develop advanced statistical and ML methods for large-scale neuroimaging to predict brain age, model disease trajectories, and discover neurological biomarkers.
• Functional Network Modeling & Deep Learning:
  Apply novel DL architectures and generative models to decode dynamic functional connectivity and brain network organization.
• CT Analysis & Urological Applications:
  Utilize computer vision and radiomics for automated segmentation, classification, treatment response prediction, and robust multi-site modeling in urological health.

• Education:
  
  Ph.D. in Computer Science, Biomedical Engineering, Applied Mathematics, Neuroscience, or a related quantitative field.
• Core Expertise:
  Strong background in machine learning, deep learning, computer vision, and medical image analysis.
• Agentic AI Focus: A strong interest in, or willingness to learn and develop, Agentic AI applications to enhance medical imaging workflows and research.
• Track Record:
  Proven ability to conduct independent research, collaborate effectively, and publish in top-tier venues.

The University of Pennsylvania is an equal opportunity employer. Candidates are considered for employment without regard to race, color, sex, sexual orientation, religion, creed, national origin (including shared ancestry or ethnic characteristics), citizenship status, age, disability, veteran status or any class protected under applicable federal, state, or local law.