We welcome students and postdoctoral researchers who want to develop physics-informed AI methods for complex polymers, soft materials, macromolecules, biomacromolecular systems, and molecular interfaces. Prior experience in polymer science is preferred but not required; we especially welcome candidates with strong backgrounds in applied mathematics, physics, statistics, machine learning, or scientific computing.
Ph.D. students
Prospective students interested in generative models, language models, AI for science foundation models, graph learning, complex polymers, and protein/RNA ensemble dynamics are encouraged to apply through UToledo graduate programs and contact the group.
A solid foundation in AI, applied mathematics, statistical physics, statistics, or scientific computing is not required but preferred. Applicants with a GitHub account are encouraged to include the link in their email.
Undergraduates
There are no formal prerequisites for undergraduate research; curiosity, reliability, and genuine interest are the most important qualities. In addition to Chemical Engineering students, we also welcome students from other engineering fields, computer science, applied mathematics, physics, statistics, and related areas.
Postdocs
Postdoctoral candidates must have experience in generative AI and are expected to contribute to AI method development. Applicants with backgrounds in machine learning, polymer science, soft matter, biomolecular modeling, or computational materials are welcome to reach out with a CV and GitHub profile link.
Applicants do not need to have a chemical engineering background. We welcome candidates from AI, computer science, statistics, chemistry, materials science, physics, applied mathematics, and related fields. Candidates with strong training in AI, computer science, statistics, or scientific computing are especially encouraged to apply.
The group places strong emphasis on AI, applied mathematics, statistics, open-source scripts, and reproducible research. Postdoctoral applicants should include at least one first-author machine-learning paper and the corresponding GitHub repository that can reproduce the reported results. If relevant code is in a private repository, company account, or otherwise restricted by confidentiality, please explain this in the email.