

We specialize in autonomous nanomaterial synthesis by integrating robotic experimentation, time-resolved characterization, and artificial intelligence. Our research focuses on learning complex relationships between synthesis conditions, reaction trajectories, and final material properties. By combining automated synthesis with machine-learning-guided experiment selection, we aim to efficiently navigate multidimensional chemical spaces and enable predictive control over nanomaterial composition, size, morphology, and functionality. This closed-loop approach provides a foundation for the inverse design and autonomous discovery of next-generation functional nanomaterials.