Postdoctoral Researcher in Scientific Machine Learning and Computational Biology
The Maddu Lab in the Department of Applied Mathematics and Statistics and the Data Science and AI Institute (DSAI) at Johns Hopkins University is seeking a highly motivated postdoctoral researcher. This fully funded, two-year position focuses on developing theoretical frameworks and computational methods at the intersection of scientific machine learning, biophysics, and computational biology.
Designation
Postdoctoral Researcher
Research Area
- Scientific machine learning
- Computational biology and bioinformatics
- Biophysical and mathematical modeling
- Statistical learning theory
- Generative modeling
- Dynamical systems and statistical physics
- Physics-informed neural networks
- Sequence-to-function modeling
Location
Maddu Lab, Data Science and AI Institute, Johns Hopkins University, United States.
Eligibility and Qualifications
- Candidates must hold a Ph.D. or equivalent doctoral degree by the position’s start date.
- Eligible disciplines include applied mathematics, statistics, physics, computer science, computational biology, or a related field.
- Strong mathematical and computational skills are desirable.
- Relevant expertise may include scientific machine learning, biophysical modeling, statistical learning theory, generative modeling, computational biology, or bioinformatics.
- Applications from candidates with diverse academic backgrounds and research experience are encouraged.
Job Description
The successful candidate will develop theory- and physics-guided machine learning and AI methods for scientific discovery in the life sciences and medicine. The Maddu Lab combines first-principles biophysical modeling with modern ML and AI techniques to create predictive and mechanistic models of complex biological processes using sparse, noisy, and high-dimensional data.
The researcher will have substantial flexibility to shape their research program. Potential projects include:
- Biophysical and mathematical modeling of intracellular and intercellular processes.
- Learning spatiotemporal dynamical models from time-series and snapshot data.
- Developing a theory of learning for physics-informed neural networks.
- Creating biophysically informed sequence-to-function models.
- Studying interpretability, robustness, generalization, and learning dynamics in large AI models using statistical physics and dynamical systems theory.
The position offers competitive compensation, comprehensive benefits, and opportunities to collaborate with researchers across applied mathematics, data science and AI, life sciences, and medicine. It is available immediately with a flexible start date.
How to Apply
Interested candidates should email the following materials to Prof. Surya Maddu:
- A current CV.
- A brief statement of research interests.
- Contact information for two to three references.
In the research statement, applicants are encouraged to identify the listed research directions that best match their interests and propose related questions they would be excited to investigate.
Last Date to Apply
Applications will be reviewed on a rolling basis until the position is filled. Early application is recommended.
Apply Link
Apply by email to Prof. Surya Maddu
