The European HORIZON-project EdgeAI targets intelligent processing of sensor data at the edge. The 48 partners will develop new electronic components and systems, processing architectures, connectivity, software, algorithms, and middleware through the combination of microelectronics, advanced signal processing and edge computing.

The TU/e research specifically addresses the processing of sensor data in building management. Knowledge on the physical properties of sensors and their imperfections are used to improve performance. Also models for human experience, wellbeing (e.g., the circadian rhythm) and performance (e.g., comfort and effectiveness of lighting) are part of the algorithmic framework. Instead of immediately addressing the issues by generic AI, we plan to explore any prior knowledge in the form of formalized, quantified mathematical models and domain insights. The challenge lies in the combination of statistical signal processing, probability and information theory and Bayesian inference. We plan to extend this to also include the combination of data of many, not always reliable sensors, in configurations that vary over time and between different installations. Sensor configurations and usage patterns widely differ from building to building and even from room to room. Hence, their observations on the underlying processes are also different. Nonetheless, there is a need for reliable deployment in a way that a system already performs well immediately after being switched on for the first time. That is, the algorithms need to be robust to the use of a variety in the use of sensors. Moreover, obtaining feedback from the user makes topics such as semi-supervised online learning, transfer learning and active inference of interest.

The PhD candidate will initially participate in system design of an edge-AI sensing and lighting control system. After an introductory phase the candidate will dive deeper into the fundamental challenges, work with real data but also enhance the theoretical framework of handling data.  This requires teamwork with other partners. The candidate is expected to actively contribute to this project as well as to research directions towards scientific breakthroughs in the above challenges. Candidates are expected to hold an MSc degree in electrical engineering, mathematics or physics and to have a solid knowledge of statistical signal processing, probability theory, information theory and artificial intelligence. In your motivation letter, we invite you to specifically address your evidenced interest in combining AI with statistical signal processing or with information theory, and in understanding the underlying physics. The project gives great opportunities for transferring meaningful innovations to industry and for secondments with industrial project partners.

A meaningful job in a dynamic and ambitious university, in an interdisciplinary setting and within an international network. You will work on a beautiful, green campus within walking distance of the central train station. In addition, we offer you:

• Full-time employment for four years, with an intermediate evaluation (go/no-go) after nine months. You will spend 10% of your employment on teaching tasks.
• Salary and benefits (such as a pension scheme, paid pregnancy and maternity leave, partially paid parental leave) in accordance with the Collective Labour Agreement for Dutch Universities, scale 27 (min. €2,541 max. €3,247).
• A year-end bonus of 8.3% and annual vacation pay of 8%.
• High-quality training programs and other support to grow into a self-aware, autonomous scientific researcher. At TU/e we challenge you to take charge of your own learning process.
• An excellent technical infrastructure, on-campus children's day care and sports facilities.
• An allowance for commuting, working from home and internet costs.
• A Staff Immigration Team and a tax compensation scheme (the 30% facility) for international candidates.