FDA Postdoctoral Fellowship - Development of Virtual Animal Models to Simulate Animal Study Results Using Artificial Intelligence (AI)

About the role

The National Center for Toxicological Research (NCTR) is seeking a postdoctoral fellow to contribute to the development of AnimalGAN, an artificial intelligence (AI)-based virtual animal model that simulates preclinical animal study outcomes. This project aims to advance FDA's regulatory science mission by supporting New Approach Methodologies (NAMs) aligned with the 3Rs principles and the FDA Modernization Act 2.0.

Responsibilities

• Investigate large-scale toxicological datasets to curate high-quality animal study data, including clinical pathology, treatment conditions, and molecular descriptors.
• Research generative AI approaches to develop AnimalGAN, modeling relationships between chemical exposure (structure, dose, duration) and multidimensional biological responses.
• Analyze molecular representations to encode chemical information for modeling.
• Contribute to the development of advanced generative models to improve stability and generalizability for high-dimensional biomedical data.
• Evaluate model performance using rigorous validation strategies, including internal testing, external benchmarking, and scenario-based assessments.
• Investigate quantitative metrics to assess agreement between simulated and observed data.
• Collaborate with interdisciplinary teams to define applicability domain and regulatory relevance.
• Participate in application studies, including hepatotoxicity assessment, and explore translational use cases such as prediction of rare adverse events.
• Contribute to peer-reviewed publications and scientific presentations.
• Collaborate with FDA scientists and external partners across toxicology, bioinformatics, and regulatory science.

Requirements

The ideal candidate should be currently pursuing or have received a doctoral degree in one of the following disciplines:

• Chemistry and Materials Sciences
• Communications and Graphics Design
• Computer, Information, and Data Sciences
• Earth and Geosciences
• Engineering
• Environmental and Marine Sciences
• Life Health and Medical Sciences
• Mathematics and Statistics
• Physics
• Science & Engineering-related
• Social and Behavioral Sciences

Qualifications

The candidate should have:

• Strong background in AI, computational toxicology, and cheminformatics.
• Experience with Python and high-performance computing.
• Excellent communication skills and ability to collaborate with interdisciplinary teams.
• Interest in regulatory science and the 3Rs principles.

Skills

The successful candidate will possess:

• Proficiency in Python programming.
• Knowledge of machine learning and deep learning techniques.
• Experience with data curation and analysis.
• Ability to work independently and collaboratively.

Benefits

The fellowship provides:

• A monthly stipend commensurate with educational level and experience.
• Structured training in AI-enabled regulatory science.
• Opportunities to publish and present findings.
• Collaboration with FDA scientists and external partners.

Pay

The stipend is determined based on the candidate's educational level and experience.

Schedule

The appointment is full-time and initially for one year, with the possibility of renewal contingent on funding availability.