Scientific Assistant

In Faculty Informatics/Electrical Engineering, Institute of Informatics/Electrical Engineering - Department IES (Prof. Dr. Bernhard Sick), the following position is to be filled as soon as possible:**:**Scientific Assistant (m/w/d), EG 13 TV-H**,**Temporary, full-time or part-time** (currently**20** or**40** per week)** **Or** **Scientific Assistant (m/w/d), (EG 14 TV-H)**,**Temporary, full-time or part-time** (currently**20** or**40** per week)** - Application deadline: 19.03.2025 - Date of hire: as soon as possible - vacancy number: - 38147 Scientific Assistant (m/w/d), EG 13 TV-H, Temporary, full-time or part-time (currently 20 or 40 per week) Part-time with half of regular working hours of a full-time employee or full-time. The position is initially limited until 31.07.2027 within the project "KonSEnz - Kontinuierlich selbstlernende Vorhersagemethoden und Services in smarten Energiemärkten und -netzen: KI-Algorithmen und Modelle“, funded by the BMWK according to the project duration (according to WissZeitVG). The possibility to work towards a doctorate is given. Or Scientific Assistant (m/w/d), (EG 14 TV-H), Temporary, full-time or part-time (currently 20 or 40 per week) Part-time with half of regular working hours of a full-time employee or full-time. The position is initially limited until 31.07.2027 within the project "KonSEnz - Kontinuierlich selbstlernende Vorhersagemethoden und Services in smarten Energiemärkten und -netzen: KI-Algorithmen und Modelle“, funded by the BMWK according to the project duration (according to WissZeitVG).The possibility to work towards a habilitation is given. The aim of the KonSEnz project is to combine methods of continuous, adaptive learning and machine learning in operation in order to meet the growing requirements of a highly data-driven energy system in terms of automation, scaling and resilience in operation. For the intelligent use of flexibility through new consumers, generators and storage systems, the demands on operational planning and thus on the predictability of more and more components and players in the energy system are increasing. At the same time, the highly dynamic nature of the system requires constant adaptation and expansion of planning and forecasting models in real time. The associated processes such as model training runs and evaluations must therefore inevitably be taken over reliably and securely by highly autonomous, computer-aided processes. The sub-project of the University of Kassel focuses on the development of algorithms and models with the help of machine learning and artificial intelligence methods. The focus is on methods of transfer learning and representation learning to facilitate the reuse of learned knowledge, methods of self-monitoring and self-awareness in technical systems to determine the need for model adaptation (e.g. for forecasting models) by the learning system itself, as well as methods of continuous learning with regard to self-reflection so that the learning system can adapt to new conditions (e.g. new plants) and guarantee the required performance. The results of the project are implementations of corresponding algorithms and models, which are being investigated in collaboration with project partners using use cases for wind power forecasts, photovoltaic forecasts and forecasts of vertical power flows at transformers. **Your tasks**: - Research in the above-mentioned areas - Support of general tasks of the IES department - Writing publications - In case of TV-H EG 14: Independent work on fundamental and challenging scientific problems in the field of machine learning. Responsible for acquisition of third-party funded projects in the field of AI for energy. Participation in the supervision of doctoral students **Requirements**: - Master in Computer Science (or closely related field) completed with very good result, preferably in the above areas. The degree required for this position must have been obtained by the starting date at the latest - In case of TV-H EG 14: PhD with a thesis on a related topic and a very good result. Very strong knowledge and experience in the above fields. Strong publication record and first experience in acquiring and leading projects. The degree required for this position must have been obtained by the starting date at the latest. - Very good fundamental knowledge in machine learning and data analysis, preferably in the above areas - Experience in programming especially in Python, but also other programming languages - Strong knowledge of AI tools, e.g., PyTorch, Tensorflow, Sklearn, Pandas, OpenCV, and Numpy - A structured working method that allows you to work in and lead a team - Independent and goal-oriented work style and enjoyment of scientific work - Very good knowledge of German and English, both written and spoken **Our offer**: As an employee of the department of Intelligent Embedded Systems you will - Being part of a highly motivated team of international researche