Postdoc: Probabilistic ML for Next-Gen Solar Materials

DTU; Kongens Lyngby; Remote; DKK 520,000 - 640,000; Full time

Job summary

DTU Compute is seeking a highly motivated postdoctoral researcher to advance probabilistic modeling and active learning for next-generation solar energy materials. You will connect synthesis conditions with material properties and device performance, using Gaussian processes, Bayesian neural networks, and uncertainty-aware representations.

The role emphasizes collaboration with the experimental team to guide synthesis and interpretation.

Qualifications

• PhD in ML, statistics, CS, applied mathematics or related field.
• Strong background in probabilistic ML and uncertainty quantification.
• Experience implementing ML methods in Python and publishing in ML-related venues.
• Excellent communication and ability to collaborate across disciplines.

Responsibilities

• Develop probabilistic models linking synthesis conditions with material properties and photovoltaic performance.
• Research active learning and Bayesian optimization for informative experiments under practical constraints.
• Integrate physical and chemical knowledge into models and identify descriptors for defects and optoelectronic properties.
• Develop multi-objective strategies for targeting bandgaps and reducing recombination losses.
• Collaborate with the experimental postdoc and DTU Electro to design experiments and interpret results.

Skills

Probabilistic ML

Gaussian processes

Bayesian neural networks

Active learning

Bayesian optimization

Experimental design

Python

Education

PhD in ML/Statistics/CS/Applied Maths

Tools

Python

Job description

DTU Compute is seeking a highly motivated postdoctoral researcher to advance probabilistic modeling and active learning for next-generation solar energy materials. You will connect synthesis conditions with material properties and device performance, using Gaussian processes, Bayesian neural networks, and uncertainty-aware representations.

The role emphasizes collaboration with the experimental team to guide synthesis and interpretation.