Assistant Scientist – AI Autonomous Synthesis and Multimodal Characterization

The Center for Nanoscale Materials (CNM) and the Advanced Photon Source (APS) at Argonne National Laboratoryinvite applications for a joint Assistant Scientist position focused on developing and applying artificial intelligence (AI) and machine learning (ML) methods for the autonomous, self-driving synthesis of nanoscale and quantum materials.

This is an exciting opportunity to help shape a new generation of closed-loop, AI-enabled experimental workflows that tightly integrate synthesis within situ and operando x-ray, electron, and optical characterization. The successful candidate will help bridge CNM’s world-class capabilities in nanofabrication and chemical synthesis with APS’s leading synchrotron measurement tools, enabling adaptive and autonomous exploration of complex materials design spaces.

In this role, you will lead a research program centered on AI-driven autonomous synthesis, including:

• Active learning and Bayesian optimization over synthesis parameters such as precursors, temperature, sequences, and pressure
• Generative and inverse-design models for materials discovery
• Closed-loop feedback frameworks that use in situ/operando scattering, spectroscopy, and imaging to guide synthesis in real time
• AI-enabled analysis of high-throughput, multimodal experimental data with uncertainty quantification
• Integration of edge computing, high-performance computing (HPC), and scientific data infrastructure to support scalable, user-facing autonomous workflows across CNM synthesis platforms and APS beamlines

This position is a joint appointment between the Theory and Modeling Group at CNM and the Computational Science and AI Group (CAI)  successful candidate will have access to Argonne’s exceptional ecosystem of facilities and expertise, including the upgraded APS, CNM’s advanced synthesis and characterization capabilities, and leadership-class computing resources at the Argonne Leadership Computing Facility.

• Lead and develop a research program in AI-enabled autonomous materials synthesis
• Design and implement closed-loop experimental workflows that integrate synthesis, characterization, and decision-making
• Develop and apply AI/ML methods for active learning, optimization, inverse design, and experiment planning
• Build analysis tools for multimodal, high-throughput experimental data, including real-time or near-real-time processing
• Collaborate closely with scientists across materials synthesis, characterization, beamline science, theory, and computing
• Contribute to the development of scalable computational and data workflows spanning edge, beamline, and HPC environments
• Publish in peer-reviewed journals, present at scientific meetings, and help shape future directions in autonomous materials research

• Ph.D. in physical chemistry, inorganic chemistry, computational materials science, chemical engineering, or a related field, along with 3–6 years of postdoctoral research experience
• A strong understanding of nanomaterials synthesis and/or in situ/operando x-ray characterization (including scattering, spectroscopy, or imaging), with demonstrated experience connecting the two
• Proven experience developing and applying AI/ML methods to autonomous experimentation, closed-loop optimization, active learning, or inverse design
• A strong publication record demonstrating innovation in AI/ML for materials synthesis, synchrotron experiments, or a closely related area
• Experience with deep learning frameworks such as PyTorch, Tensor Flow, or JAX
• Experience with optimization and active-learning libraries such as BoTorch, GPyTorch, or scikit-learn
• Strong programming skills, especially in Python, including integration with experimental control systems or lab-automation frameworks
• Ability to model Argonne’s core values of impact, safety, respect, integrity, and teamwork

• Experimental control and orchestration frameworks such as ROS, Bluesky, or EPICS
• Laboratory automation and robotic synthesis platforms
• Generative models, reinforcement learning, or agentic AI approaches for materials discovery and experiment planning
• Multimodal data fusion and real-time data reduction for…