PhD Student

**Job Description**
This PhD position focuses on cutting-edge machine learning methods, specifically predictive and generative AI for materials. The project involves developing neural diffusion techniques to design materials with targeted optical properties and creating multi-fidelity predictive models that integrate data from quantum simulations and experiments, utilizing equivariant graph neural networks with tensor embeddings. The goal is to train these methods in a closed-loop framework to enable iterative improvement and seamless feedback between generative design and predictive modeling for next-generation energy materials discovery.

**Skills & Abilities**
• Demonstrated experience in deep learning, preferably including some exposure to graph neural networks or geometric deep learning.
• Proven experience with implementing machine learning methods in Python and PyTorch.
• Familiarity with materials physics (a plus).
• High level of motivation and creative problem-solving skills.
• Excellent communication and writing skills in English.

**Qualifications**
Required Degree(s) in:
• Master’s degree (or equivalent academic level to a two-year master’s degree)

Note: We’ve analyzed the actual job post using AI, for more details visit the original job post by clicking on “Apply Now”!