PHD Position Scientific Machine Learning for Scientific Foundation Models
· DELFT, Netherlands ·
- Employment
- Contract
- Category
- ML ai
PhD Position Scientific Machine Learning for Scientific Foundation Models (Delft, NL, 2628 CD) Delft University of Technology (TU Delft)
Software Engineering, Data Science
Posted on Aug 31, 2026
Job description
We invite applications for a fully funded PhD position in the area of Scientific Machine Learning (SciML), which integrates data-driven machine learning techniques with established scientific knowledge, such as physical laws, differential equations, and domain-specific constraints, to model, simulate, and understand complex systems. The project will explore modern SciML methods, including physics-informed neural networks, neural operators, hybrid physics-ML approaches, and emerging foundation-model paradigms for scientific data.
Scientific machine learning is increasingly important in domains where observations are indirect, incomplete, expensive, or noisy, and where reliable models must respect the structure of the underlying physical system. For example, in subsurface investigation, one may aim to infer hidden geological or physical structures from measurements such as seismic, electromagnetic, or other indirect observations. Similar challenges also arise in climate and geoscience, energy systems, materials modelling, fluid dynamics, and other scientific and engineering domains where data-driven models must interact with physical knowledge. Such problems raise fundamental machine learning challenges: how to learn from limited and heterogeneous data, how to combine data with physics-based models, how to solve inverse problems under uncertainty, and how to build models that generalize across different physical settings.
Building on this motivation, the project focuses on the definition, development, and analysis of scientific foundation models: large-scale, generalizable models trained across diverse scientific datasets that aim to capture reusable representations of physical systems and can be adapted to a wide range o...
Software Engineering, Data Science
Posted on Aug 31, 2026
Job description
We invite applications for a fully funded PhD position in the area of Scientific Machine Learning (SciML), which integrates data-driven machine learning techniques with established scientific knowledge, such as physical laws, differential equations, and domain-specific constraints, to model, simulate, and understand complex systems. The project will explore modern SciML methods, including physics-informed neural networks, neural operators, hybrid physics-ML approaches, and emerging foundation-model paradigms for scientific data.
Scientific machine learning is increasingly important in domains where observations are indirect, incomplete, expensive, or noisy, and where reliable models must respect the structure of the underlying physical system. For example, in subsurface investigation, one may aim to infer hidden geological or physical structures from measurements such as seismic, electromagnetic, or other indirect observations. Similar challenges also arise in climate and geoscience, energy systems, materials modelling, fluid dynamics, and other scientific and engineering domains where data-driven models must interact with physical knowledge. Such problems raise fundamental machine learning challenges: how to learn from limited and heterogeneous data, how to combine data with physics-based models, how to solve inverse problems under uncertainty, and how to build models that generalize across different physical settings.
Building on this motivation, the project focuses on the definition, development, and analysis of scientific foundation models: large-scale, generalizable models trained across diverse scientific datasets that aim to capture reusable representations of physical systems and can be adapted to a wide range o...