Research Assistant PostDoc (m/f/d)

We at the LFB are convinced that the most groundbreaking breakthroughs arise where different perspectives meet. Our mission is to close the gap between complex raw data and real clinical as well as robotic applications and to convert abstract sensor signals into insights that change life. We cultivate a cooperative and integrative research culture – a living community in which pioneering work is brought to life in the fields of imaging technology, computer science and embodied intelligence. Become part of a visionary research team at the Chair of Imaging and Imaging (LFB) of RWTH Aachen. We develop physical AI systems – robots and embodied agents that perceive the physical world, logically follow and act. Inspired by state-of-the-art vision language action models (VLA), we extend the boundaries of robot learning, reinforcing learning from experience and the use of foundation models on robot platforms in practice. This postdoc site is of central importance for a moment of foundation: the establishment of a new research group for physical AI at one of Europe's leading technical universities, embedded in a network of leading industrial and clinical partners. The RWTH is certified as a family-friendly university. RWTH offers a variety of health, counselling and prevention services (e.g. university sports) as part of a university health management. There is a wide range of training and the possibility of obtaining a job ticket for employees and civil servants.

As a postdoc researcher and co-founder of the Physical AI Group, you develop methods that enable robots to learn from demonstrations, corrections and own experiences, and use them in real environments. • Vision-Language Action (VLA) models: design and implementation of VLA architectures that integrate vision, language and action for skillful manipulation, building on large pre-trained vision-Language backbones (e.g. VLMs with 5 billion parameters). • Strengthening learning from experience: development of RL pipelines – Offline-RL, predominantly conditioned strategies – which allow robots to grow beyond pure imitation and achieve robustness at human level and superhuman robustness through autonomous experience. • mastery of tasks with a long time horizon: investigation of the assignment of merits over extended tasks by means of learned value functions, enabling robots to identify and correct cumulative errors in complex real scenarios. • Sim-to-Real-Transfer & World Models: Overcome of Simulation and Use Using World Models, Self-Monitored Presentations (JEPA, DINOv3) and Transfer Techniques for Robust Generalization. • Medical & clinical robotics: collaboration with imaging and clinical groups for the use of physical AI in health robotics, combining LFB's sensor expertise with embodied intelligence.

• Complete university studies (master or comparable) and doctorate in computer science, electrical engineering, robotics, physics or a related subject • Knowledge of deep learning and experience with Reinforcement Learning and Imitation Learning • Practical experience with PyTorch and training large models; Confidence with VLA or Foundation model architectures is a great advantage • List of publications in renowned journals (NeurIPS, ICML, ICLR, CoRL, ICRA or equivalent) • Motivation to work at the interface of Physical AI, embodied intelligence and real application • Excellent communication skills in English; German is advantageous, but not required

What we offer:• A co-founder role in a new research group for physical AI with direct influence on their research agenda and culture – supported by a established industrial partners in the field of humanoid robotics • A leading research environment at one of the best technical universities in Europe with access to robot platforms and unique clinical and industrial data sets • Mentoring for the development of an independent research management, including support for funding applications (DFG, BMBF, EU Horizon) and preparation for a future professorship • Active cooperation with partners from industry and medical technology, with opportunities to achieve real impact in practice • Possibilities for top-class publications, guest lectures and participation in international conferences • Flexible, family-friendly working conditions according to the guidelines of RWTH Aachen Our offer The employment is in the employment relationship. The place shall be occupied at the next possible time and shall be limited to 3 years. There is the option to extend the job for another three years. The temporary employment is carried out within the framework of the time-limits of the science-time contract law. It is a full-time job. The grouping depends on the TV-L. The place is rated with EG 13 TV-L. The job description is aimed at all sexes. We want to promote the careers of women at RWTH Aachen University and are therefore looking forward to applicants. Women are preferably taken into account in the case of equal suitability, competence and professional performance, provided You are underrepresented in the organisational unit and, if not in the person of a competitor, outweigh the reasons. Applications for suitable people with difficulty are expressly desired. For the purposes of equal treatment, we ask you to waive an application photo. Information on the collection of personal data pursuant to Articles 13 and 14 of the General Data Protection Regulation (GDPR) can be found at https://www.rwth-aachen.de/dsgvo-information-bewerbe