JOB DESCRIPTION

Are you passionate about developing intelligent agents that can continuously evolve through social interactions? Do you want to contribute to cutting-edge research on generative causal models that enable adaptive collaboration in dynamic environments?
We are seeking a motivated PhD candidate to join our research team working on causal representations for open-ended, embodied social intelligence. This project aims to develop a groundbreaking generative framework that enables agents to continuously evolve through social interactions in unconstrained, multiparty environments.
Current AI systems struggle to gain new knowledge in dynamic environments and to reason about human behavior in unconstrained settings. We believe that embodied agents collaborating with humans require not only representations of the physical world but also rich causal models of their interaction partners. Your research will focus on identifying the causal factors that guide human behaviors and environmental changes, allowing agents to continually adapt through open-ended learning.
You will be embedded within the larger Pattern Recognition and Bioinformatics Group at TU Delft, comprising sub-groups in Computer Vision, Pattern Recognition, and Human-Oriented Machine Intelligence. You will be advised by Dr. Chirag Raman (Tapri Lab, TU Delft), Dr. Jan-Willem van de Meent (AMLab, UvA), and Dr. Frans Oliehoek (Sequential Decision Making Group, TU Delft).
This project is part of a larger research effort within the Hybrid Intelligence Center, where you will have the opportunity to collaborate with researchers across multiple universities and disciplines. The project specifically connects to the Robotic Surgery case study, involving close collaboration with Dr. Dalibor Vasilic at ErasmusMC.

JOB REQUIREMENTS

We are looking for a candidate with:

• An MSc degree in Computer Science, Artificial Intelligence, Robotics, or a related field
• Strong background in machine learning, particularly in generative latent variable modeling and/or (multi-agent) reinforcement learning.
• Solid programming skills in Python, experience with deep learning frameworks (e.g., PyTorch, Jax).
• Comfort with 3D mathematics and spatial reasoning concepts.
• Good engineering skills for implementing and evaluating algorithms in real-world settings; familiarity with simulation environments (e.g. Isaac Sim) is a plus.
• Experience with robotics platforms is a plus but not required.
• Experience with conducting user studies is beneficial but can be developed during the PhD.
• Excellent written and verbal communication skills in English (C1 or equivalent).
• A collaborative mindset and the ability to work in an interdisciplinary team.

We aim to create hybrid intelligence for everyone, see also our Diversity Statement. To do this, we need an inclusive and diverse team of researchers. We especially encourage people from underrepresented groups to apply for this job.

Please refer the Job description for details