Postdoctoral Fellow: Multimodal Biomedical AI Research

The University of Texas at Austin; Austin (TX); On-site; USD 57,000 - 70,000; Full time

Job summary

The University of Texas at Austin invites applications for a Postdoctoral Fellow in the TEAM-AI Lab within the Department of Quantitative and Systems Health Sciences. The role focuses on multidisciplinary health data science, multimodal AI, and responsible AI.

You will design algorithms, coordinate multi-institutional work, and translate real-world health data into clinical insights, with mentorship from lab faculty.

Qualifications

• PhD must have been earned within the last three years.
• Strong background in one or more of the listed areas: generative and trajectory modeling, multimodal NLP, ontological engineering, regulatory science and explainable AI.

Responsibilities

• Lead design and implementation of mixture-of-experts neural architectures and RL pipelines for counterfactual disease trajectory simulation.
• Architect and evaluate multi-site cardiotoxicity risk prediction models using structured EHRs, NLP notes, and imaging features.
• Coordinate AI and comput., phenotyping work streams within national multi-institution networks to standardize and validate data elements.
• Build deep language models and NLP pipelines to extract phenotypes and biomarkers from progress notes.
• Develop semantic knowledge graphs and database query architectures for perioperative pathophysiology research.
• Publish first-author or co-author manuscripts in major informatics and ML venues.
• Perform other duties as assigned.

Skills

Generative modeling

Mixture-of-experts

Reinforcement learning

Multimodal NLP

Knowledge graphs

CDE development

High-performance computing

Big data analytics

Education

PhD in Biomedical Informatics or related quantitative field

Job description

The University of Texas at Austin invites applications for a Postdoctoral Fellow in the TEAM-AI Lab within the Department of Quantitative and Systems Health Sciences. The role focuses on multidisciplinary health data science, multimodal AI, and responsible AI.

You will design algorithms, coordinate multi-institutional work, and translate real-world health data into clinical insights, with mentorship from lab faculty.