Postdoctoral Research Associate- AI​/ML Accelerated Theory Modeling & Simulation Microelectronics

Postdoctoral Research Associate- AI/ML Accelerated Theory Modeling & Simulation for Microelectronics

The Center for Nanophase Materials Sciences (CNMS) is seeking a Postdoctoral Research Associate to support research directed towards developing novel AI/ML algorithms that can incorporate multi-scale computational simulations to aid with data fusion across multiple modalities of experiments with the final goal of discovering novel materials phenomena or even new materials. Focus will largely be in developing and deploying such AI/ML algorithms, closely collaborating with theorists and experimentalists to realize physics‑models and/or physics‑aware ML‑models that can bridge length/time scales, to provide improved mechanistic insights into nanomaterials response.

Bulk of the work will be on novel materials for next‑generation microelectronic devices (e.g. oxide ferroelectrics and 2D memristive materials).

As a Postdoctoral Research Associate, you will contribute to research in these areas, bridging state‑of‑the‑art atomistic and mesoscopic simulation methods as indicated above as well as nanoscale experiments with domain‑informed AI/ML algorithms. In addition to fundamental science discovery, the research will pursue development of automated workflows and novel ML‑approaches that allow integration of different theory, simulation, and experimental protocols. The research is designed to provide opportunities for development of your experience and scientific vision.

The applicant will also work closely with scientists at CNMS as well as those involved in a multi‑institution collaboration (~30 researchers) spanning Oak Ridge National Laboratory, Argonne National Laboratory, Northwestern University, and Lawrence Berkeley National Laboratory to address grand challenge problems in materials for next‑generation microelectronics applications.

The position resides in the Theory & Computation Section, Center for Nanophase Materials Sciences (CNMS), Physical Sciences Directorate (PSD) at ORNL and will be jointly supervised by Dr. P. Ganesh, Dr. Rama Vasudevan and Dr. Vitali Starchenko.

Major Duties/Responsibilities:

• Develop and validate AI/ML models that can be used for knowledge extraction (e.g. discovery of governing equations; correlative analysis across length/time‑scales etc.) from multi‑scale simulations and multi‑modal experiments.
• Perform data fusion using novel AI/ML approaches to seamlessly transfer information from simulations and experiments into data ingestion pipelines for model refinement.
• Perform multi‑scale simulations (e.g. DFT / atomistic / phase‑field simulations) to train AI/ML models.
• Conduct scientific research on ferroelectrics and/or 2D memristive materials.
• Create and maintain datasets in databases on in‑house data storage resources working closely with ORNL’s workflow and data management scientists.
• Meaningfully collaborate with experimental groups involved in the project.
• Report and publish scientific results in peer‑reviewed journals in a timely manner.
• Present results at international scientific conferences and meetings.
• Deliver ORNL’s mission by aligning behaviors, priorities, and interactions with our core values of Impact, Integrity, Teamwork, Safety, and Service. Promote equal opportunity by fostering a respectful workplace – in how we treat one another, work together, and measure success.

Basic Qualifications:

• A PhD in Physics, Materials Science, Chemistry, or closely related field completed within the last 5 years.
• Sound understanding of advanced ML concepts and architectures and hands‑on experience with open‑source AI/ML packages (such as pytorch, scikit‑learn, tensor flow, JAX etc.).

Preferred Qualifications:

• Good grasp of concepts in solid‑state physics, ferroelectrics and/or 2D materials.
• Strong background in developing and/or applying materials simulation methods, such as atomistic simulations using electronic‑structure and/or machine‑learning interatomic potentials (MLIPs) and phase field modeling, particularly related to materials for next‑generation microelectronics (e.g. oxide ferroelectrics, 2D materials and related systems).
• Strong familiarity with AI/ML algorithms, for…