Victor Alves

Victor Alves is an assistant professor in the Department of Chemical Engineering at Carnegie Mellon University. His research lies at the intersection of process systems engineering (PSE), optimization, and machine learning (ML). He develops mathematical and computational methods that combine physics-based models with data-driven methods to improve the design, operation, and control of complex, industrial-scale systems.

His work in hybrid scientific machine learning combines first-principles engineering models with ML components that learn unknown or not fully understood process dynamics from available data, improving predictive accuracy while preserving physical laws, engineering constraints, and interpretability. His research also includes generative modeling, model-based design of experiments, uncertainty quantification, process operability, and plantwide control. He also studies the use of large language models (LLMs) to orchestrate workflows for process modeling, optimization, and control. Alves develops open-source scientific software used by the PSE community, including Opyrability and Metacontrol for process operability and plantwide control, respectively. He applies his research to chemical and advanced manufacturing, biopharmaceutical production, energy, and petrochemical systems, often in collaboration with industrial and federal research partners.

Alves earned his Ph.D. in chemical engineering from West Virginia University in 2024 and his B.S. (2017) and M.S. (2020) in chemical engineering from the Federal University of Campina Grande in Brazil. Before joining the Carnegie Mellon faculty, he was a postdoctoral fellow in the Department of Chemical Engineering at CMU, where his research focused on hybrid modeling and model-based design of experiments for biopharmaceutical processes, differentiable programming, and dynamic optimization. He also has industrial experience in petrochemical process engineering and in developing software for plantwide process control for the oil and gas sector.