Postdoctoral Appointee – Materials Informatics and Autonomous Synthesis
Core
Developing AI/ML methods for autonomous materials discovery and synthesis, building data resources and predictive models to guide experiments in self-driving laboratories.
Role type
Postdoctoral Researcher (Materials Informatics & Autonomous Synthesis)
Builds
Data-driven methods, predictive models, and closed-loop decision frameworks for autonomous synthesis platforms.
Domain
Materials Science / Machine Learning / Autonomous Laboratories
Deliverable
production ML models
Required skills
Python, NumPy, pandas, scikit-learn, PyTorch, TensorFlow, surrogate modeling, active learning, Bayesian optimization, uncertainty-aware modeling, data integration, workflow automation
Preferred skills
Reinforcement learning for experiments, autonomous/robotic lab platforms, cheminformatics, RDKit, multimodal data fusion, NLP, text mining, descriptor engineering
Technologies
Polybot, NumPy, pandas, scikit-learn, PyTorch, TensorFlow, RDKit
Responsibilities
Develop machine learning-ready data resources by integrating literature and experimental data; Build surrogate and predictive models connecting composition, structure, and properties; Design adaptive experimental design workflows to guide autonomous platforms; Integrate AI/ML workflows into closed-loop synthesis and fabrication; Contribute to strategies for generating diverse datasets and reproducible computational pipelines; Share research outcomes through publications, software, and datasets.