Research Assistant in Artificial Intelligence for Power Electronics Design

At AAU Energy, a fixed-term position as Research Assistant in Artificial Intelligence for Power Electronics Design, is open for appointment from January 1, 2027, or soon hereafter. The duration of the position is 2 years. Your work tasks Your work will include developing, training and evaluating machine-learning models based on circuit data, board geometries, simulation results and design images. You will develop surrogate models that approximate thermal and electromagnetic solvers, enabling faster evaluation of design alternatives. The position may also involve computer vision for recognizing circuit structures, component placements and printed circuit board geometries from photographs or other images. In addition, you will investigate graph-based methods for representing circuit relationships, evaluating design rules and generating or testing hypotheses for circuit designs. You will contribute to the development and verification of agentic workflows, where artificial intelligence systems combine models, tools and design rules to reason through and support electronics design tasks. You will prepare datasets, document computational workflows, validate model performance and share results with colleagues working in artificial intelligence, power electronics, semiconductors and software development. The position is offered within the research field of Artificial Intelligence for Power Electronics Design and contributes to AAU Energy’s focus areas of Digital Transformation and Artificial Intelligence, and Energy Efficiency in Components and Systems. The Research Assistant will be affiliated with the Section of Power Electronics System Integration and Materials. Your competencies You have a relevant master’s degree in computer science, electrical engineering, electronics, artificial intelligence or a related field, and you are interested in working at the intersection of machine learning and power electronics design. You have a solid foundation in applied machine learning. Familiarity with electronic systems, including printed circuit boards, circuit topologies, components and the physical principles that influence electrical, thermal and electromagnetic performance, will help you engage with the engineering context of the role. You have practical experience developing, training and evaluating machine-learning models, and you can translate complex engineering challenges into data-driven methods suited to a research environment. You are comfortable working with...

Summary and match are AI-generated; verify details on the original posting.

Listed via EURES. All sources