This PhD position at Eindhoven University of Technology offers an exciting opportunity to advance the field of mobile autonomous robotics through cutting-edge research in end-to-end AI architectures. As part of the NWO Perspectief FIND project, you will collaborate with leading research organizations and companies, including TNO and NXP, to develop innovative AI models that enable robots to autonomously navigate and interact with open-world environments. The research focuses on Vision Language Models (VLMs), Multi-modal Large Language Models (MLLMs), and Vision Language Action models (VLAs), targeting spatial scene understanding and spatial reasoning for real-world robotic applications.

The core challenge is to achieve robust spatial understanding that allows robots to operate safely and reliably in new environments with minimal human input. The project emphasizes the development of efficient end-to-end models capable of real-time operation, balancing fast tasks (such as collision prevention) and slower reasoning tasks, all within the constraints of embedded systems' limited compute and energy resources. Daily activities will include literature review, hypothesis generation, network architecture design, training method development, validation setup, and dissemination of findings through presentations and publications. Independence, critical thinking, and teamwork are highly valued, given the rapid pace of AI advancements.

The position is embedded in the Mobile Perception Systems (MPS) laboratory of the Signal Processing Systems (SPS) group within the Electrical Engineering department. The MPS lab is renowned for its research in efficient AI architectures for vision modalities, regularly publishing in top-tier venues such as CVPR, ICCV, and IEEE RAL. Supervision will be provided by Associate Professor Gijs Dubbelman, Assistant Professor Daan de Geus, and expert researchers from TNO and NXP. The FIND program brings together five universities, eleven companies, and two knowledge institutes to develop foundation models for the Dutch high-tech industry, with a strong focus on edge deployment, privacy, and timely decision-making. Real-world validation domains include HealthTech, smart industry, and autonomous mobility.

Applicants must have a master’s degree in Computer Science, Artificial Intelligence, Robotics, or a closely related field, with a high-quality MSc thesis (preferably publishable or already published at top-tier venues). Required skills include knowledge of state-of-the-art AI architectures (especially transformers), strong machine learning theory and practice, experience with deep learning frameworks (e.g., PyTorch), interdisciplinary teamwork, teaching motivation, and fluency in English (C1 level or higher).

The position offers full-time employment for four years, with an intermediate assessment after nine months. Benefits include a competitive salary (scale P: €3,059–€3,881/month), year-end bonus (8.3%), annual vacation pay (8%), pension scheme, paid pregnancy and maternity leave, partially paid parental leave, commuting and home working allowances, Staff Immigration Team, and a 30% tax compensation scheme for international candidates. The university provides high-quality training programs, excellent technical infrastructure, on-campus childcare, and sports facilities.

To apply, submit your application online via the provided link, including a cover letter, CV with publications, and contact information for three references. Only complete applications will be considered. The vacancy will remain open until filled, with a deadline of March 4, 2026. For further information, contact Floor de Groot (HR advisor) at [email protected]. Please note that applications sent by email or post will not be processed, and a pre-employment screening may be part of the selection procedure.