Postdoc: Causal & Multimodal AI for Health Data Science

Indiana University; Indianapolis (IN); On-site; USD 55,000 - 70,000; Full time

Job summary

Indiana University School of Medicine in Indianapolis invites applications for a Postdoctoral Fellow in Biostatistics and Health Data Science.

The role focuses on artificial intelligence for healthcare, multimodal data analysis, and causal AI, collaborating with computer scientists, clinicians, and public health researchers to develop deployable, trustworthy methods that improve patient outcomes and health-system operations.

Qualifications

• Ph.D. by start date in a relevant area (see qualifications).
• Strong ML/deep learning foundation with modality-focused expertise.
• Experience with healthcare data (EHR, clinical text, imaging, omics).
• Proficiency in Python and ML tooling (PyTorch, scikit-learn), Git, and experiment tracking.
• Excellent written and oral communication and collaboration skills.

Responsibilities

• Lead original research in multimodal and causal AI for health; design, implement, and evaluate algorithms and pipelines.
• Build reproducible research pipelines and maintain codebases (prefer Python).
• Apply causal inference and discovery frameworks to clinical questions.
• Translate proposed methods into real-world clinical workflows.
• Contribute to grant proposals and research reports.

Skills

Python

ML/deep learning

Multimodal learning

Time-series modeling

NLP

Clinical/Healthcare data

Experiment tracking

Git

PyTorch

Weights & Biases

Communication skills

Education

Ph.D. in Computer Science, Biomedical Informatics, Health Data Science, Biostatistics, or closely related area

Tools

Git

Weights & Biases

PyTorch

scikit-learn

Job description

Indiana University School of Medicine in Indianapolis invites applications for a Postdoctoral Fellow in Biostatistics and Health Data Science.

The role focuses on artificial intelligence for healthcare, multimodal data analysis, and causal AI, collaborating with computer scientists, clinicians, and public health researchers to develop deployable, trustworthy methods that improve patient outcomes and health-system operations.