Ph.D. students
The group currently has two to three fully funded Ph.D. student positions available for Spring 2027 and Fall 2027. We primarily recruit students with backgrounds in chemical engineering and closely related fields who are interested in developing physics-informed AI methods for polymers and biomacromolecules. Please apply through UToledo Chemical Engineering graduate admissions and contact the group.
Funding: These Ph.D. positions cover tuition and provide a stipend for living expenses. In the first year, students are supported by the department through a part-time teaching assistantship (TA) while also beginning research with Prof. Shi. From the second year onward, students transition to a research assistantship (RA) funded by the PI. For further details, please contact the Graduate Student Director, Prof. Maria Coleman.
Applicants with an active GitHub account are encouraged to include the link in their email.
For all prospective Ph.D. students, regardless of academic background: Please read at least one of the papers listed below before sending your first email to Prof. Shi. Before requesting an informal Zoom meeting, please prepare slides covering the following two parts:
- Your own research (6–8 minutes): Explain your research questions, methods, specific contributions, and main results.
- Your understanding of one of our papers (6–8 minutes): Discuss the main problem, approach, key findings, and your thoughts or questions.
Please choose one of the following papers, available on our publications page. Each paper has a corresponding public GitHub repository listed in the main text:
- Measuring Differences in Protein Allosteric Graphs Constructed via Molecular Dynamics Simulations (2026)
- MacroSimGNN: Efficient and Accurate Calculation of Macromolecule Pairwise Similarity via Graph Neural Network (2026)
- Calculating Pairwise Similarity of Polymer Ensemble via Earth Mover’s Distance (2024)
- Quantifying Pairwise Similarity for Complex Polymers (2023)
- Using Transfer Learning to Leverage Prior Knowledge in the Prediction of Adhesive Free Energies between Polymers and Surfaces (2023)
- Predicting Adhesion Free Energies of Polymer-Surface Interactions with Machine Learning (2022)
Additional guidance for applicants with backgrounds in Computer Science, AI, Software Engineering, or Data Science
We also welcome applicants from computer science, AI, software engineering, and data science who have a genuine interest in our research. The following guidance is intended specifically for applicants with these backgrounds, particularly those with limited prior exposure to chemical engineering or closely related research.
Career uncertainty is an understandable concern, but a Ph.D. should be motivated by genuine interest in the research, rather than primarily by limited job opportunities. As an advisor, Prof. Shi wants students to choose research they can see themselves enjoying and pursuing with sustained interest over the next four to five years. Reading our papers and exploring the accompanying code can help you decide whether you would enjoy working on these questions and developing the knowledge needed to pursue them.
If you remain interested in pursuing a Chemical Engineering Ph.D. in the Shi Group, please explain in your first email which aspects of the work interest you and any questions from your reading. When requesting an informal Zoom meeting, please include the slides described above. Prof. Shi will review your materials and follow up about a possible meeting to discuss your interests and potential fit in more depth.