Jiang Group | Computational Materials and Product Design

Shengli Jiang, PhD

Assistant Professor

Department of Chemical Engineering

University of South Carolina

About the Jiang Group

We develop physics-informed machine learning and AI methods to understand, predict, and design soft materials and chemical products for energy and sustainability.

These materials pose a multiscale design problem: molecular structure, processing conditions, and product performance are tightly coupled. We build predictive models that bridge these scales, learning from simulation, theory, and data while respecting physical constraints.

Our Approach

Machine Learning and AI Methodology Physics-informed neural networks, geometric and topological deep learning, and generative models.

Molecular Simulation Connecting molecular structure, dynamics, and interactions to macroscale properties.

Materials and Product Design Translating predictive understanding into materials that are high‑performing, synthesizable, stable, and scalable.

Research Areas

Polymer Recycling and Upcycling Designing selective and efficient processes for plastic waste valorization using AI-guided molecular understanding.

Polymer Electrolytes and Membranes Engineering ion-conducting polymers and separation membranes through multiscale modeling and machine learning.

Polymer Rheology and Complex Fluids Predicting flow behavior and processability of architecturally complex polymers from molecular design.

Join Us

We are recruiting two PhD students (start: Fall 2026 and Spring 2027) and one postdoctoral researcher to work on AI‑driven soft materials design.

If you’re drawn to problems at the intersection of machine learning, molecular simulation, and theory, we’d be glad to hear from you.

View openings & apply →

news

Aug 24, 2026	New course launching this fall — ECHE 589: Machine Learning in Chemical Engineering is now open for enrollment. MWF 10:50–11:40 AM. Learn more.
Apr 12, 2026	The Jiang Group is officially launching at the University of South Carolina!