Doctoral researcher in vision-language-action models

Is an international research university with a distinctly multilingual and interdisciplinary character.
at the University of Luxembourg is a leading international research and innovation
We play an instrumental role in Europe by fueling innovation through research partnerships with industry, boosting R&D investments leading to economic growth, and attracting highly qualified talent. We look for researchers from diverse academic backgrounds to contribute to our projects in areas such as: Network Security, Information Assurance, Model-driven Security, Cloud Computing, Cryptography, Satellite Systems, Vehicular Networks, and ICT Services & Applications.
Conducting research on a predefined topic and producing results
Disseminating results through scientific publications and/or patents
Participating in outreach activities to promote SnT's research activities and citizen science
This attractive PhD position is in close collaboration with our industrial partner, POST Luxembourg ( ). The successful candidate will join the Computer Vision, Imaging, and Machine Intelligence (CVI²) research group ( ) led by Prof. Djamila Aouada, to pursue a PhD in Computer Vision, with a focus on multimodal reasoning and Vision-Language-Action (VLA) models for autonomous driving. The research will aim to enhance the safety, generalization, and efficiency of VLA-based driving systems, in particular their robustness to rare and novel scenarios, their capacity for long-horizon reasoning, and their efficient inference for real-world deployment. The candidate will conduct research on predefined topics that contribute to SnT's and POST's R&D activities. This position will require conducting full-scale research, from reviewing state-of-the-art methods to implementing and validating tangible solutions and disseminating results.
Master's degree in electrical engineering, computer science, applied mathematics, or a related field
Strong programming skills in Python/C/C++/MATLAB
Experience with multimodal learning, vision-language models (VLMs), large language models, or autonomous driving perception and planning would be a strong asset
Capacity to adapt and thrive in a fast-paced research environment
Multilingual and international character. Member of The Guild of European Research Intensive Universities
An exceptional research environment, supported by skilled staff and high-quality equipment. Research statement and topics of particular interest to the candidate (300 words)
Preferably, sharing a GitHub/GitLab webpage listing completed projects in Computer Vision
Please apply ONLINE formally through the HR system. All qualified individuals are encouraged to apply. We encourage applications from individuals of all backgrounds and are dedicated to upholding equality and respect for our employees and students. Contract Type: Fixed Term Contract 36 Month
Work Hours: Full Time 40.0 Hours per Week
Internal Title: Doctoral Researcher
The yearly gross salary for every Doctoral researcher at the UL is EUR 43445 (full time).