Postdoctoral Researcher in Scientific Machine Learning and Computational Biology

Johns Hopkins University • Baltimore, MD

17h • Onsite

About The Position

The Maddu Lab in the Department of Applied Mathematics and Statistics and Data Science and AI Institute (DSAI) at Johns Hopkins University (JHU) is seeking a highly motivated postdoctoral researcher interested in developing theoretical frameworks and computational methods at the interface of scientific machine learning, biophysics, and computational biology. The Maddu Lab integrates first-principles biophysical modeling with modern ML/AI techniques to build predictive, mechanistic models of complex biological processes from sparse, noisy, and high-dimensional data. Complementarily, we use concepts from statistical physics and dynamical systems theory to develop theoretical frameworks for understanding the behavior and learning dynamics of large AI models, with an emphasis on interpretability, robustness, and generalization. The Maddu Lab emphasizes the judicious development of theory- and physics-guided ML/AI tools to enable scientific discovery in the life sciences and medicine. The postdoctoral researcher will have substantial flexibility in shaping their research program, with potential projects including: (i) Biophysical and mathematical modeling of intracellular and intercellular processes; (ii) Learning spatiotemporal dynamical models from time-series and snapshot data; (iii) Theory of learning in physics-informed neural networks; (iv) Biophysically informed sequence-to-function models.

Requirements

• Ph.D. (or equivalent doctoral degree) in applied mathematics, statistics, physics, computer science, computational biology, or a related field by the start date.
• Strong mathematical skills.
• Strong computational skills.

Nice To Haves

• Expertise in scientific machine learning.
• Expertise in biophysical modeling.
• Expertise in statistical learning theory.
• Expertise in generative modeling.
• Expertise in computational biology.
• Expertise in bioinformatics.

Responsibilities

• Developing theoretical frameworks and computational methods at the interface of scientific machine learning, biophysics, and computational biology.
• Integrating first-principles biophysical modeling with modern ML/AI techniques to build predictive, mechanistic models of complex biological processes.
• Using concepts from statistical physics and dynamical systems theory to develop theoretical frameworks for understanding the behavior and learning dynamics of large AI models.
• Developing theory- and physics-guided ML/AI tools to enable scientific discovery in the life sciences and medicine.
• Shaping their research program with potential projects including: (i) Biophysical and mathematical modeling of intracellular and intercellular processes; (ii) Learning spatiotemporal dynamical models from time-series and snapshot data; (iii) Theory of learning in physics-informed neural networks; (iv) Biophysically informed sequence-to-function models.

What This Job Offers

• Job Type: Full-time
• Career Level: Entry Level
• Education Level: Ph.D. or professional degree