Postdoc in Machine Learning for Energy Materials - DTU Compute

DTU - Technical University of Denmark; Kongens Lyngby; On-site; DKK 420,000 - 540,000; Full time

Job summary

DTU Compute in Denmark seeks a postdoctoral researcher to develop probabilistic modeling and active learning methods for next-generation solar energy materials. You will work with DTU Compute and the Thin-Film Photovoltaics Group to advance machine learning for materials discovery and experimental design.

You will build models that connect synthesis conditions to material properties, publish results, and contribute to teaching and supervision of PhD and MSc/BSc students.

Qualifications

• Strong background in probabilistic ML, incl. Gaussian processes, Bayesian nets, uncertainty quantification.
• Experience implementing ML methods in Python with scientific computing frameworks.
• Strong publication record in ML or closely related fields.
• Excellent communication and interdisciplinary collaboration.
• Formal qualification: PhD degree; knowledge of materials science or photovoltaics is a plus.

Responsibilities

• Develop probabilistic models linking synthesis conditions, material properties and photovoltaic performance.
• Research active learning and Bayesian optimization for informative experiments under constraints.
• Integrate physical and chemical knowledge into models and identify informative descriptors.
• 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.
• Publish scientific papers and present results at ML conferences and interdisciplinary venues.
• Contribute to supervision of PhD and MSc/BSc students.

Skills

Gaussian processes

Bayesian neural networks

Uncertainty quantification

Active learning

Bayesian optimization

Experimental design

Python

PyTorch

GP libraries

Education

PhD in a relevant field

Tools

Python

PyTorch

GP frameworks

Job description

Job Description

Do you want to develop machine learning methods that help uncover how materials are formed and guide the next experiment? If you are building a career as a researcher in machine learning and are passionate about developing methods for scientific discovery, we offer an excellent opportunity to advance your research. We are seeking a highly motivated postdoctoral researcher to join DTU Compute and develop probabilistic modeling and active learning methods for next-generation solar energy materials.

The position is funded by a Villum Synergy grant within the project "Data-driven design of tunable chalcogenide thin films for next-generation indoor and tandem photovoltaics." You will join an interdisciplinary collaboration between DTU Compute and the Thin-Film Photovoltaics Group at DTU Electro, working closely with a dedicated experimental postdoc.

Project Description

How can we learn from limited experimental data to understand materials synthesis and decide which experiment to perform next? This project addresses this question for antimony-based chalcogenide thin films for indoor and tandem solar cells. Their properties depend on complex interactions between synthesis conditions, which influence crystal structure, defect formation, and ultimately photovoltaic performance.

You will develop probabilistic models that connect synthesis conditions with material properties and device performance, combining experimental data with physical and chemical knowledge. Relevant approaches include Gaussian processes, Bayesian neural networks, and uncertainty-aware representation learning. Alongside accurate prediction, a central aim is to identify informative descriptors and understand which processing conditions govern bandgap, defects, and recombination losses.

The models will form part of a closed-loop framework in which active learning and Bayesian optimization guide successive synthesis experiments. This creates methodological challenges in learning from small datasets, calibrating predictive uncertainty, incorporating experimental constraints, and balancing scientific understanding with performance optimization.

Responsibilities

• Develop probabilistic models linking synthesis conditions, material properties, and photovoltaic performance.
• Research active learning and Bayesian optimization methods for selecting informative experiments under practical constraints.
• Integrate physical and chemical knowledge into models and identify descriptors that help explain defect formation and optoelectronic properties.
• Develop multi-objective strategies for targeting bandgaps and reducing recombination losses.
• Work closely with the experimental postdoc and researchers at DTU Electro to design experiments, interpret results, and evaluate the closed-loop framework.
• Publish scientific papers and present results at leading machine learning conferences and relevant interdisciplinary venues.
• Contribute to teaching and the supervision of PhD and MSc/BSc students.

Qualifications

• A strong background in probabilistic machine learning, with experience in areas such as Gaussian processes, Bayesian neural networks, uncertainty quantification, active learning, Bayesian optimization, or experimental design.
• Proven experience implementing machine learning methods in Python using relevant scientific computing frameworks.
• A strong publication record in machine learning or closely related fields.
• Motivation and creative problem-solving skills, with an interest in developing methods that address experimental challenges.
• Excellent communication and writing skills in English and an enthusiasm for interdisciplinary collaboration.

Experience with scientific machine learning, incorporating domain knowledge into models, or learning from experimental data would be an advantage. Prior expertise in materials science or photovoltaics is not required.

As a formal qualification, you must hold a PhD degree (or equivalent).

We offer

DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and terms of employment

The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. In addition, supplements can be negotiated in accordance with DTU's salary structure for scientific staff: www.inside.dtu.dk/en/human-resources/during-employment/salary/salary-structures .

The period of employment is 2 years. The starting date is 1 January 2027 (or according to mutual agreement). The position is a full-time position.

You can read more about career paths at DTU here .

Further information

Further information may be obtained from Mikkel N. Schmidt, [e-mail] / www.mikkelschmidt.dk .

You can read more about DTU Compute at www.compute.dtu.dk .

If you are applying from abroad, you may find useful information on working in Denmark and at DTU at DTU – Moving to Denmark .

All interested candidates irrespective of age, gender, disability, race, religion or ethnic background are encouraged to apply. As DTU works with research in critical technology, which is subject to special rules for security and export control, open-source background checks may be conducted on qualified candidates for the position.

DTU Compute - Department of Applied Mathematics and Computer Science - is an internationally recognised academic environment with over 400 employees and 10 research sections. We broadly cover digital technologies within mathematics, data science, computer science, and computer engineering, including artificial intelligence (AI), machine learning, internet of things (IoT), chip design, cybersecurity, human-computer interaction, social networks, fairness, and data ethics. Our research is rooted in basic research and centres on mathematical models of the physical and virtual world, as a basis for the analysis, design, and implementation of complex systems. We focus on ensuring that our research results contribute to creating a better society by supporting areas such as health, green transition, energy supply, and life science. We collaborate with universities, public and private organisations, and companies in Denmark and abroad, and through DTU’s startup ecosystem, we encourage innovation and entrepreneurship. We have a strong ethical, human, and sustainable approach that ensures integrity in our work. Therefore, we strive for and take responsibility for driving the democratisation of digital technologies, so that everyone has the opportunity to actively participate in the development, and we ensure a continued open, democratic, and inclusive society for the benefit of all. At DTU Compute, we value diversity, inclusion, and a flexible work-life balance. Read more here: www.compute.dtu.dk .

DTU - For the benefit of society since 1829

DTU is one of Europe's leading elite technical universities. Through research and education at an international top level, we create solutions to the major societal challenges of our time and help secure Europe's global leadership in sustainable technological development. Since Hans Christian Ørsted founded DTU almost 200 years ago, our mission has remained the same: We develop and create value through the natural and technical sciences for the benefit of society. DTU has 13,800 students, 1,600 PhD students, and 6,500 employees. We work in an international environment and have an inclusive, stimulating, and informal work culture. DTU has campuses in all parts of Denmark and in Greenland and collaborates with the best universities around the world.