AI-Enabled Catalyst Discovery Postdoctoral Researcher Job Idaho Falls area,Idaho USA,Research/Development

Idaho National Laboratory is hiring a postdoctoral researcher in Chemical Engineering, Materials Science, Computer Science, Data Science, Applied Mathematics or closely related field to support our Integrated Energy Technologies Department. The postdoctoral researcher will lead the development of an artificial intelligence (AI)-enabled catalyst discovery workflow that integrates experimental data, mechanistic understanding, and machine learning to accelerate heterogeneous catalyst development for propane dehydrogenation.

This position lies at the interface of catalysis, data science, and scientific software development, supporting the creation of a closed loop experimental and computational platform for autonomous catalyst optimization.

Our team works a 9x80 schedule located out of our Idaho Falls facility with every other Friday off.

Primary Responsibilities Include

Design, develop, and maintain machine learning workflows for catalyst performance prediction and inverse catalyst design.
Develop forward predictive models that relate catalyst synthesis parameters, physiochemical characterization, and transient kinetic descriptors to catalytic performance metrics including yield, selectivity, and stability.
Implement inverse-design algorithms that recommend new catalyst compositions and synthesis conditions for experimental validation.
Integrate heterogeneous datasets generated from high-throughput synthesis, catalyst screening, transient kinetic measurements, and reactor scale testing into a unified data pipeline.
Develop automated data preprocessing, feature engineering, uncertainty quantification, model validation, and candidate-ranking workflows.
Interface machine learning models with the project’s graph-based ontology and FAIR data infrastructure to enable automated model training and data ingestion.
Collaborate closely with catalyst synthesis, high-throughput screening, transient kinetics, and reactor testing teams to incorporate newly generated experimental data into iterative model refinement.
Evaluate model performance using statistical cross-validation and experimental validation across catalyst development scales, from research powders through technical catalyst forms.
Develop reproducible software, documentation, and visualization tools that support workflow deployment and long-term maintainability.
Contribute to publications, technical reports, software releases, presentations, and project reviews.

Required

PhD in Chemical Engineering, Material Science, Computer Science, Data Science, Applied Mathematics, or a closely related field.
PhD requirements must be completed by commencement of appointment and within the previous 5 years.
Experience developing machine learning models using Python and scientific computing libraries (e.g., PyTorch, Tensor Flow, scikit-learn).
Experience with scientific data analysis, statistical learning, and predictive modeling.
Strong programming skills and experience with software version control.
Demonstrated ability to work in multidisciplinary research teams.

The Ideal Candidate Will Possess

Experience applying machine learning to chemistry, catalysis, material science, or reaction engineering.
Familiarity with Bayesian optimization, active learning, inverse design, or uncertainty quantification.
Experience with graph databases, knowledge graphs, or ontology development.
Experience developing scientific workflows for automated or…