41 machine-learning-"https:"-"https:"-"https:"-"https:"-"UCL" Postdoctoral positions at Argonne
Sort by
Refine Your Search
-
familiarity in machine learning (ML) and artificial intelligence (AI). This role is pivotal in evaluating the economic competitiveness of the U.S. in the production and manufacturing of energy-related materials
-
++, or JavaScript Experience with AI or machine learning techniques, including large language models or agentic systems Experience developing or integrating interactive visualization systems, including web-based
-
to study chemical transformations in materials. 2. Artificial Intelligence Applications: - Leveraging conventional machine learning techniques for materials property prediction and Bayesian approaches
-
applying machine learning or other elements of artificial intelligence to solving significant scientific or engineering problems Interest in software development, with particular emphasis on the Python
-
beyond the Standard Model, including effective field theories and perturbative QCD, phenomenology at current and future colliders, as well as emerging areas in Artificial Intelligence, Machine Learning
-
-principles and atomistic simulations with machine-learned interatomic potentials to: Model reaction pathways on metal-oxide surface, including adsorption, reactions and diffusion steps. Construct atomistic
-
programming, interfacing hardware, and developing machine-learning methods highly desirable. The researcher will join an Argonne funded project with interdisciplinary team of material scientists, computer
-
operations is preferred, working knowledge of machine learning and artificial intelligence methods is highly desirable The successful candidate will demonstrate expertise in accelerator physics, accelerator
-
science, including electronic structure methods molecular dynamics, and scientific machine learning. Experience with High-Performance Computing (HPC) systems and intelligent workflows. Demonstrated
-
on developing machine-learning surrogates for electronic structure and electrostatic potential and using these models to predict structural and electronic evolution under applied bias. Methods may include density