Postdoctoral Appointee – Materials Informatics and Autonomous Synthesis

About the role

The Center for Nanoscale Materials (CNM) at Argonne National Laboratory invites applications for a postdoctoral research position focused on developing AI/ML methods for autonomous materials discovery and synthesis. We are seeking a creative and collaborative researcher who is excited by the opportunity to help shape the future of autonomous synthesis and self-driving laboratories.

Responsibilities

• Develop machine learning-ready data resources for materials by integrating literature, in-house, and newly generated experimental data
• Build surrogate and predictive models that connect composition, molecular structure, synthesis and processing conditions, morphology, and device-relevant properties
• Design active learning, Bayesian optimization, uncertainty-aware modeling, and other adaptive experimental design workflows to guide experiments and improve data efficiency in autonomous platforms such as the Polybot
• Work closely with experimental researchers to integrate AI/ML workflows into closed-loop autonomous synthesis, fabrication, and characterization; translate model predictions into experimental campaigns; and update models using newly acquired data
• Contribute to strategies for generating diverse, high-value datasets, identifying meaningful descriptors and representations, and building reproducible computational pipelines, workflow automation, and data infrastructure that support long-term autonomous laboratory capabilities
• Share research outcomes through publications, presentations, software, datasets, and internal reports

Requirements

• Recent or soon-to-be-completed PhD (within the last 0-5 years) in chemistry, chemical engineering, materials science, polymer science, physics, computer science, and/or data science
• Demonstrated accomplishments in materials informatics, scientific machine learning, or AI-guided experimental design
• Strong Python and scientific computing skills, including experience with tools such as NumPy, pandas, scikit-learn, and machine learning frameworks such as PyTorch, TensorFlow, or similar
• Experience developing surrogate models, predictive models, or adaptive learning workflows for scientific or engineering applications
• Strong interest in working closely with experimental researchers in a laboratory-centered environment
• Evidence of independent research productivity through publications, software, datasets, or similar outputs
• Excellent communication skills, the ability to work effectively in interdisciplinary teams
• Ability to model Argonne’s core values of impact, safety, respect, integrity, and teamwork

Preferred Qualifications

• Experience with active learning, Bayesian optimization, adaptive experimental design, reinforcement learning for experiments, or uncertainty quantification
• Background in electronic polymers, conjugated polymers, organic semiconductors, soft materials, electrochemical materials, or related functional materials
• Experience integrating literature, experimental, and simulation datasets into unified, machine learning-ready workflows
• Familiarity with cheminformatics or polymer informatics, molecular representations, descriptor engineering, RDKit, characterization-informed modeling, multimodal data fusion, interpretable machine learning, NLP, text mining, or automated extraction of materials data from the literature
• Experience with workflow automation, data infrastructure, database development, reproducible research pipelines, and collaborative environments that span computation, data science, and experiment