Postdoc in data-driven control of building and district energy systems

Updated: over 1 year ago
Job Type: FullTime
Deadline: 18 Dec 2022

Empa - the place where innovation starts

Empa is the research institute for materials science and technology of the ETH Domain and conducts cutting-edge research for the benefit of industry and the well-being of society.

The Urban Energy Systems Laboratory develops models and concepts for the planning and operation decentralized energy system technologies based on renewable energy and innovative districts, including prototypes and demonstration plants. To strengthen our scientific team we are looking for a

Postdoc in data-driven control of building and district energy systems

You will lead a funded project on "Scalable deep reinforcement learning algorithms for energy and building climate control " where learning based control as well as semantic data structures are key topics. You will investigate research questions directly, while coordinating research activities within the project team.


You will develop scalable and transferable modeling and control methods and pipelines, and apply them in simulation as well as experimentally. You will have the freedom to develop and execute your research ideas in close collaboration with our team and our external scientific and industry partners.

You will support the dissemination of research findings across the community, which includes collaborating with other lab members and institutes and publishing in scientific journals and conferences. Open science principles are strongly supported/encouraged.

Your tasks

  • Model and controller development in the domain of building, mobility and district energy systems
  • Experimental validation of developments on the Empa demonstrators (NEST , move , ehub ) 
  • Publish in scientific journals and conference proceedings
  • Project coordination and project ideation
  • Support of project acquisition
  • Supervise MSc students and Co-supervise PhD students

Your profile

  • PhD related to data-driven control of energy and/or building systems
  • Applied experience in buildings and energy systems simulation and control
  • Background in Machine learning, in particular: neural networks and deep reinforcement learning (theoretical and practical)
  • Open science mindset
  • Experience in using Python is preferable
  • Prior experience or knowledge of semantic data modeling is an advantage
  • Excellent written and oral communication skills in English are mandatory, German language skills are a strong plus 

We offer a stimulating, international and collaborative research environment at a leading research institution with an excellent infrastructure and a broad interdisciplinary surrounding. As an institution of the ETH Domain, we offer good employment conditions and plenty of opportunities for your professional development. The workplace is Dübendorf, close to Zürich. The contract will be initially limited to two years with a possibility of extension. The position is available form 01.01.2023 or upon agreement.

For further information about the position please Philipp Heer [email protected] and visit our websites www.empa.ch/web/s313 and Empa-Video

We look forward to receiving your online application including a letter of motivation, CV, diplomas with transcripts and contact details of two referees. Please upload the requested documents through our webpage. Applications via email will not be considered.

Empa, Patricia Nitzsche, Human Resources, Ueberlandstrasse 129, 8600 Dübendorf, Switzerland.



Similar Positions