Doctoral student in machine learning for sustainable welding materials
Core
Developing effective algorithms for rapid, robust predictions of welding materials and establishing composition–processing–property relationships using machine learning.
Role type
Doctoral student (Ph.D.) in machine learning for materials science
Builds
Predictive models and generative AI approaches for new welding material formulations
Domain
Sustainable energy systems, welding science, computational materials
Deliverable
production ML models
Required skills
Machine learning algorithms, first-principle methods (density functional theory, molecular dynamics), thermodynamics of materials, chemistry/physics of metals and metal oxides
Preferred skills
Generative AI, active-learning approaches
Technologies
Density functional theory, molecular dynamics
Responsibilities
Develop AI and ML models to predict material formulations; conduct research in collaboration with industry partners; teach undergraduate courses (up to 20% of time)
Seniority
Early-career researcher (Ph.D. candidate)
