Thesis: Development of a smart embedded device for multimodal AI interaction(m/w/x)

City: Paderborn Date: Apr 29, 2025 # Thesis: Development of a smart embedded device for multimodal AI interaction Smart embedded devices are becoming increasingly important as they act as intelligent, networked interfaces between the physical world and cloud-based AI services. The challenge and at the same time the attraction lies in using limited resources (computing power, energy, space) to develop systems that reliably capture and process input data such as images and speech and provide comprehensible feedback. This topic opens a wide range of possible applications - from barrier-free assistance systems and smart educational devices to applications in industry or everyday life. **What you will do** In cooperation with the start-up around the AI companion Lexie, the aim of this thesis is to develop a compact, screen-free smart embedded device that can capture several types of input - in particular image and audio data - and transmit them to cloud-based AI services for processing. Feedback to the user is provided exclusively via acoustic feedback (e.g. voice output). By dispensing with a display, the focus shifts to multimodal processing (image and voice) and intuitive interaction with the device. Various hardware constellations will be tested in order to analyse their influence on recognition quality, system latency and other parameters. **What you bring to the table** * You are studying computer science, embedded systems or a comparable study programme * You are interested in embedded AI applications and have some experience in programming microcontrollers and sensor technology * You are motivated and like to work independently **What you can expect** * A strong team culture with flat hierarchies is a matter of course for us. This means: high esteem and trust * Professional supervision and specialist support in the preparation of the student research project/thesis * Exciting and practical application example from a young start-up * Flexible working from home to combine studies and work in the best possible way We value and promote the diversity of our employees' skills and therefore welcome all applications - regardless of age, gender, nationality, ethnic and social origin, religion, ideology, disability, sexual orientation and identity. Severely disabled persons are given preference in the event of equal suitability. **Job Segment:** Cloud, Embedded, Computer Science, Developer, Technology, Research