Sort by
Refine Your Search
-
implement pioneering agentic AI workflows for autonomous materials characterization. We are building the next generation of AI-powered laboratories, where intelligent agents can formulate hypotheses, run
-
agents for X-ray spectroscopy by integrating large language models (LLMs) with physics-aware spectroscopy workflows. The researcher will work closely with a multidisciplinary team of X-ray physicists and
-
Postdoctoral Appointee - Investigation of Electrocatalytic Interfaces with Advanced X-ray Microscopy
, physics-informed AI agent that accelerates discovery in catalysis science—particularly for the CO₂ reduction reaction (CO₂RR) and oxygen evolution reaction (OER). The postdoc will design and perform
-
databases and retrieval-augmented generation (RAG) and integrate agentic AI systems to meet the demands of large-scale fine-tuning and inference. The postdoc will also work on design and implement agentic-AI
-
- Exploring Foundational Models and Agentic AI to address challenges in energy storage and conversion. Position Requirements Candidates must meet the following qualifications: 1. Educational Background: - A
-
computational research. They are intrinsically driven, goal-oriented, and can work collaboratively with others. Working closely with the CPS divison, the postdoc will leverage AMReX and the LBM to develop
-
. The cosmology effort at Argonne includes staff members from the CPAC group, the Computational Science division, and the HEP Detector Group. The group also includes many postdocs, and a number of graduate and
-
undergraduates. Postdocs benefit from strong interactions with experts in applied mathematics, computer science, device physics, materials science, and statistics, as well as access to world-leading supercomputing
-
data Familiarity with agentic LLM-based approaches and related technologies (e.g., RAG, MCP, A2A) Interest in interfacial phenomena and defect dynamics in materials across scales Job Family Postdoctoral
-
-Informed Neural Networks (PINNs) and geometric deep learning. Experience with active learning, agentic workflows, or other methods for autonomous experimentation. Familiarity with high-performance computing