Context In many real-world systems, purely data-driven models often lack physical interpretability and generalization capabilities, especially when training data are limited or noisy. To overcome these limitations, Knowledge-Guided Deep Learning (KGDL) integrates knowledge, such as equations, physical constraints, or domain rules, directly into the learning process. This hybrid approach combines the strengths of traditional physics-based modeling and modern machine learning, leading to models that are both accurate and physically consistent. With the growing availability of sensor data (e.g., temperature, humidity, pressure or weight), KGDL offers a powerful framework to enhance predictive performance, improve robustness to unseen conditions, and reduce the need for large labeled datasets. In this context, this internship aims to design and develop deep learning models guided by domain-specific knowledge for sensor-based prediction tasks. The work will involve identifying appropriate ways to embed knowledge and validating the approach on real sensor datasets. Missions The intern will contribute to the design and development of knowledge-guided deep learning models for predictive tasks using sensor data. The main objectives and tasks include: Data preprocessing and exploratory analysis of real-world sensor datasets, including variables such as temperature, humidity, and weight. Design and implementation of deep learning architectures that incorporate domain-specific knowledge. Experimentation with various knowledge integration strategies. Exploration of knowledge-guided multimodal deep learning approaches to investigate how integrating additional modalities (e.g., RGB images/videos, thermal, or depth data) can enhance model performance and generalization. Evaluation of model performance and interpretability, and benchmarking against purely data-driven approaches. Required Qualifications The candidate should meet the following criteria: • Education: Currently enrolled in an engineering school or pursuing a Master’s degree (or equivalent); • Technical skills: Strong knowledge of deep learning; • Programming: Excellent command of Python and PyTorch; • Ability to work independently with rigor, initiative, and strong organizational skills; • Familiarity with software development best practices is highly appreciated. Duration: 6 months Location: Multitel, Parc Initialis 2, Rue Pierre et Marie Curie, 7000 Mons, Belgium. Application process: Interested candidates should email their application (single PDF named Lastname_Firstname_InternshipTitle.pdf, including CV, cover letter, and academic transcript), indicating their intended start and end dates and the internship title in the email subject line. Depending on the candidate’s profile and interests, the internship may take either a research-oriented or an industry-oriented focus. Multitel is a research and technological innovation center based in Mons, Belgium, supporting industrial players in the development of cutting-edge technological solutions in Artificial Intelligence, Applied Photonics, Networks and Cybersecurity, IoT and Embedded Systems, and Railway Certification. With its multidisciplinary expertise and commitment to excellence, Multitel actively contributes to strengthening industrial competitiveness and fostering innovation at both regional and international levels. Multitel’s Artificial Intelligence Department has strong expertise in machine learning and data-driven technologies, applied to a wide range of data modalities (images, videos, time series, 3D point clouds, spectral and satellite data, and audio signals) as well as diverse application domains (healthcare, agriculture, defense, security, etc.). The department has expertise covering the entire data value chain, from data collection and preprocessing to model development, deployment, and real-world integration.