The Nonlinear Systems and Control group is seeking a talented and ambitious Postdoctoral Researcher to develop machine learning-enabled approaches for predictive modelling and state estimation for fundamental applications within physical sciences.
The main research responsibilities involve building cutting edge machine learning techniques for sequential data modelling, including Physics-informed Machine Learning and Koopman Operator-based representation framework, towards building interpretable predictive models for complex multi-physics dynamical systems as well as towards designing observer-based state estimators from output timeseries data measurements. The research also involves development of uncertainty quantification techniques for the learnt models.
You will also have opportunities to contribute to open-source computational tools and datasets, teach master-level courses, and advise doctoral students. You will closely collaborate with Prof. Mari Lundström’s group as well as industry partners and leading research institutions within the Nordics and the EU. Additionally, you will have the opportunity to participate in multidisciplinary initiatives within the Aalto House of AI.
You have a recent doctoral degree in electrical engineering, control engineering, computer science, applied mathematics or a related field. Programming proficiency in Python is required, and hands-on experience with ML libraries such as PyTorch is expected. Theoretical understanding and experience with multi-physics modelling of electrochemical processes can be a plus. We value candidates who are collaborative team players, intellectually curious, and open to exploring new research directions. A track record of publications in recognised journals and conferences in the field is expected.