We are seeking a talented Computational Scientist to carry out impactful and boundary-pushing research at the intersection of AI and Drug Development. While there have been major advances in the development of AI/ML algorithms, to enable Human-Machine Partnership in the context of Drug Development it is crucial that the models be explainable and generalizable. To this end, new methodologies need to be developed and demonstrated on large, longitudinal clinical datasets.
The AI Postdoctoral Fellow will develop methodologies for generating causal explanations from Neural-ODE models, to help surmount the existing challenges associated with the use of saliency maps on longitudinal data. A second focus revolves around using mechanism-informed Graph Neural Networks (GNNs) to enhance the generalizability of neural-ODE models, by leveraging the insight that models built on established mechanistic basis tend to enable better extrapolations. We expect that the research outcome will be published in top tier journals as well as influence the best practices within the drug development industry.
The candidate should possess a PhD in a quantitative discipline (Computer Science/Computational Sciences, Biomedical Informatics, Mathematics, Physics, Engineering, Pharmacometrics, Statistics, and others) and a track record of developing and implementing innovative ideas. Knowledge and/or experience with Neural-ODE, Graph Neural Networks and other Deep Learning architectures for longitudinal data are highly desirable. Experience with Pharmacometrics and Quantitative Systems Pharmacology (QSP) models is not required, but would be a plus. Excellent communications skills and a strong publication record are expected.