Postdoctoral Research Associate, AI​/ML Chemical Reactions and Automation

We are seeking a Postdoctoral Research Associate who will focus on the development and application of artificial intelligence and machine learning (AI/ML) methods to understand and guide chemical reactions. The research will combine experimental spectroscopy data and molecular simulations to develop predictive models, estimate prediction uncertainty, and guide the selection of new experiments using Bayesian optimization and active learning. The successful candidate will also develop and demonstrate an automated workflow, model training, and experimental recommendations in close collaboration with experimental and computational researchers.

This position resides in the Center for Molecular Biophysics (CMB), Biosciences Division (BSD) at Oak Ridge National Laboratory (ORNL).

Requisition

We are seeking a Postdoctoral Research Associate who will focus on the development and application of artificial intelligence and machine learning (AI/ML) methods to understand and guide chemical reactions. The research will combine experimental spectroscopy data and molecular simulations to develop predictive models, estimate prediction uncertainty, and guide the selection of new experiments using Bayesian optimization and active learning. The successful candidate will also develop and demonstrate an automated workflow, model training, and experimental recommendations in close collaboration with experimental and computational researchers.

This position resides in the Center for Molecular Biophysics (CMB), Biosciences Division (BSD) at Oak Ridge National Laboratory (ORNL).

• Develop and apply deep learning multimodal AI/ML models that combine spectroscopy data, molecular structures, reaction conditions, and simulation results to understand chemical reactions and guide new experiments.
• Prepare and organize experimental and computational datasets, including data cleaning, spectral preprocessing, quality checks, and consistent recording of experimental conditions.
• Develop Bayesian optimization and active learning methods to recommend new experimental conditions.
• Develop and demonstrate an automation pipeline that processes new data, retrain models, and recommend the experiments. Work with the experimental team to connect this pipeline with laboratory software and instruments where feasible.
• Maintain reproducible code and workflows, communicate results to the project team, and contribute to publications, presentations, and project reports.

• A Ph.D. in chemical engineering, chemistry, computer science, applied mathematics, physics, or a related field.
• Experience with Python, C, and/or C++ applied programming.
• Proficiency in programming and simulation tools such as Python, C, C++, and/or ML frameworks (Scikit-learn, Keras, Tensor Flow, PyTorch).
• Ability to work with experimental and computational researchers and communicate results clearly.
• Strong analytical and problem-solving skills, with the ability to work independently on complex research problems.

• Strong background in applying machine learning and deep learning methods to chemistry, molecular properties, chemical reactions, spectroscopy, or related scientific problems.
• Experience with Bayesian optimization, active learning, and Gaussian process model, particularly for problems with limited experimental data.
• Experience building automated scientific workflows, including data ingestion, model training, prediction, and tracking of experimental results.
• Familiarity with molecular simulations, quantum chemistry, or reaction kinetics and the use of computational results in machine learning.
• Experience using high-performance computing (HPC), parallel job submission scripts, software…