Jona Beysens

The e-Media Research Lab at KU Leuven, part of the Department of Electrical Engineering (ESAT), offers a PhD position focused on distributed AI-driven embedded intelligence for ubiquitous sensing in the sky. The lab is renowned for its research in signal processing, data analytics, machine learning, and Human-Computer Interaction, with impactful contributions to healthcare, Industry 5.0, biomedical sensing, and education. This project leverages cutting-edge tinyML technologies to enhance intelligence and energy efficiency in resource-constrained devices. As climate change intensifies, clear-air turbulence in aviation and natural disasters are becoming more frequent, highlighting the need for improved weather forecasting and environmental monitoring. Current forecasts in the troposphere are limited to 10 days, and the mechanisms by which Earth's low altitudes (ELA) affect weather patterns are not fully understood. In-situ sensing in ELA can extend forecasts, improve ozone observation, and enhance cosmic radiation monitoring. The rapid development of unmanned aerial vehicles (UAVs) presents a promising solution for densifying ELA monitoring, but challenges remain in handling the vast, heterogeneous data and scaling control infrastructure for airborne sensors. This PhD project addresses these challenges by developing ultra-reliable spatiotemporal (4D) predictions using trustworthy, distributed AI intelligence across heterogeneous aerial nodes. The research will design an aerial platform with distributed computing in a mobile network of resource-constrained devices, incorporating uncertainty-aware AI models to maximize resource efficiency and trustworthiness. The second phase will focus on integrating sensing, computation, and communication for context-aware, self-organized aerial networks. Applicants should have a master’s degree in Electrical Engineering or Telecommunication Engineering, be ranked in the top 10% of their class, and possess strong grades. Essential skills include fluency in English, a solid background in AI-enabled signal processing and machine learning, and strong interpersonal abilities for teamwork in an international environment. Experience in wireless communication and networking fundamentals is a valuable asset. Proof of English proficiency (IELTS, TOEFL, or similar) is recommended. The position offers a PhD scholarship for up to four years, with pre-doc support for non-EER applicants. KU Leuven provides a stimulating research environment, state-of-the-art laboratories, and opportunities for international collaboration. Successful candidates will earn a PhD from a highly ranked university and participate in conferences and workshops with top EU research teams. KU Leuven is committed to diversity, inclusion, and equal opportunity, fostering an environment of open dialogue and respect. For accessibility or support questions, applicants are encouraged to reach out via email. To apply, submit your CV, motivation letter, transcripts, and proof of English proficiency through the KU Leuven online portal. For further information, contact Prof. dr. ir. Jona Beysens or Prof. dr. ir. Hazem Sallouha by email.

The e-Media Research Lab at KU Leuven, part of the Department of Electrical Engineering (ESAT), is offering a PhD position focused on hardware-aware embedded AI for innovative healthcare applications. The lab is renowned for its research in signal processing, data analytics, machine learning, and Human-Computer Interaction, with impactful contributions to Industry 5.0, bio-medical sensing, healthcare, and education. This project aims to advance hardware-aware Neural Architecture Search (NAS) to automatically design efficient deep learning models tailored for specific embedded hardware platforms. Successful candidates will work on developing models for resource-constrained, standalone devices such as wearable sensors, assistive robotics, and implantable systems, where real-time performance, energy efficiency, and reliability are paramount. Unlike traditional NAS approaches, this research integrates hardware characteristics directly into the model design process, enabling neural networks that are both accurate and aligned with the capabilities of diverse embedded platforms. The project involves studying fine-grained hardware behavior, creating efficient evaluation mechanisms for candidate architectures, and designing adaptive search processes based on hardware insights. The resulting framework will support on-device intelligence without cloud connectivity, ensuring privacy, robustness, and predictable performance in sensitive healthcare settings. While healthcare is the primary focus, the modular framework will also be applicable to other real-time embedded AI domains, such as automotive and human-computer interaction, where efficient on-device processing is essential. Applicants should have a Master’s degree in Electrical Engineering, be ranked within the top 10% of their class, and possess exceptional grades. A strong background in AI-enabled signal processing and machine learning algorithms, experience with embedded platforms (NPU, FPGA, ARM Cortex-M), and proficiency in C, C++, and Python are required. Excellent communication skills, fluency in English, and the ability to work in an international team are essential. Submission of IELTS, TOEFL, or similar English proficiency test is recommended if available. The position offers a PhD scholarship for up to 4 years (subject to positive evaluations), with up to 1 year of pre-doc support for non-EER applicants. KU Leuven provides a stimulating research environment, state-of-the-art laboratories, and opportunities to participate in international conferences, workshops, and collaborations with top EU research teams. Graduates will earn a PhD title from a highly ranked university and receive thorough scientific training. KU Leuven is committed to diversity, inclusion, and equal opportunity, fostering a respectful and socially safe environment. For accessibility or support questions, applicants are encouraged to reach out via the provided contact email. To apply, submit your CV, motivation letter, transcripts, and English proficiency test results (if available) through the KU Leuven online portal. For further information, contact Prof. dr. ir. Jona Beysens at [email protected].

KU Leuven is advertising a fully funded PhD in Hardware-Aware Embedded AI for Healthcare (ref. BAP-2026-229) within the e-Media Research Lab in Belgium. The project sits at the intersection of embedded AI , machine learning , signal processing , electrical engineering , and healthcare technology . The research focuses on hardware-aware neural architecture search (NAS) to design efficient AI models for resource-constrained devices. The goal is to create AI that is optimized for specific hardware, energy-efficient, real-time capable, and privacy-preserving by running on-device rather than in the cloud. Research applications include wearable health sensors , assistive robotics , implantable medical devices , and broader edge AI use cases such as automotive systems and human-computer interaction. The work involves designing hardware-aware AI models, integrating hardware constraints into model design, developing evaluation and optimization methods, and working with embedded systems such as FPGA , ARM , and NPU . Eligibility highlights include a Master’s degree in Electrical Engineering or a closely related field , strong academic performance (top 10% preferred), a solid background in machine learning and signal processing, experience with embedded systems, and programming skills in Python and C/C++ . Applicants should also be fluent in English and able to work well in a team. The position is fully funded for up to 4 years . The deadline is 21 May 2026 . To apply, prepare a CV with grades, a motivation letter of up to one page, transcripts, and English proficiency evidence if available, then contact Prof. Jona Beysens as indicated in the vacancy.