Postdoc Position in Cooperative Perception & Multiterminal AI for Autonomous Vehicles

1 - Working at the VUB

For more than 50 years, the Vrije Universiteit Brussel has stood for freedom, equality and solidarity, and this is very much alive on our campuses among students and staff alike. 

 

At the VUB, you will find a diverse collection of personalities: innovators pur sang, but above all people who are 100% their authentic selves. With some 4,000 employees, we are the largest Dutch-speaking employer, in the private sector, in Brussels; an international city with which we are only too happy to connect and where (around) our 4 campuses are located. 

 

Add to this our principle of free research - in which self-reflection, a critical attitude and an open, creative mind around scientific and social issues are central - and you have a university that is fundamentally groundbreaking and pioneering in education and research. In short: the VUB all over again. 

 

Moreover, the VUB is a member of EUTOPIA, an alliance of like-minded European universities, all ready to reinvent themselves.

2 - Position description

The Faculty of Engineering, Department Elektronica en informatica, research group Electronics and Informatics: Research – Development - Innovation, is looking for a postdoctoral researcher. 

 

More concretely your work package contains: 

We invite you for a fully-funded postdoctoral researcher within the prestigious European Research Council (ERC) Consolidator Grant “Reinventing Multiterminal Coding for Intelligent Machines (IONIAN).”

 

Why cooperative perception?

State-of-the-art autonomous vehicles can miss a critical obstacle when their camera is blinded by sun glare, or their LiDAR beam is blocked by a truck. To reach level-4/5 autonomy, we need teamwork: nearby vehicles, drones, and roadside units must co-perceive their environment, sharing and fusing complementary sensor views in real time. Yet raw video and point-cloud streams are massive, wireless links are unreliable, and safety demands that information be both timely and trustworthy.

 

IONIAN tackles this bottleneck head-on. We will re-invent multi-agent AI, cooperative vision, and compression protocols so fleets of intelligent machines can perceive the world—robustly, efficiently, and in a trustworthy manner—even when individual sensors fail or are occluded.

 

Position Overview

As a postdoctoral researcher, you will forge a novel framework for cooperative perception by disrupting today’s most vibrant research threads in AI:

• Generative Diffusion & 3D/4D Scene Synthesis: Re-design diffusion and NeRF-style models so multiple agents jointly reconstruct a scene.
• Cooperative Scene Understanding: Re-design semantic segmentation and object-detection models in a cooperative perception setting.
• Semantic-Aware Compression & Network Information Theory: Derive new rate–distortion–reliability bounds, design adaptive codecs that prioritise safety-critical bits, and close the
• loop between information theory and AI models for cooperative perception.
• Real-World Validation: Deploy and benchmark your algorithms on our autonomous vehicle, mobile robots, and UAV testbeds.

 

You will:

• Publish in CVPR/ICCV/ECCV, NeurIPS/ICLR, INFOCOM/ISIT and leading IEEE journals (T-PAMI, T-IP, T-IT, T-CSVT and T-SP).
• Collaborate with top EU & US labs and industry partners.
• Mentor PhD and Master’s students and assist in project follow-up.

 

For this function, our Brussels Humanities, Sciences & Engineering Campus (Elsene) will serve as your home base. 

3 - Profile

What do we expect from you?

 

• PhD degree in Electrical Engineering, Computer Science, Applied Mathematics, or related field

 

• Solid grounding in computer vision, machine learning, image, video, or point cloud processing.
• Record of first-author publications in reputable conferences like NeurIPS, ICLR, ICML, CVPR, and top-tier journals like IEEE T-IP, T-SP, T-PAMI.
• Proficiency with deep learning (PyTorch/TensorFlow/JAX).
• Genuine interest in: deep learning for generative AI, 3D vision, and compression.
• Strong programming skills; analytical rigour; excellent English.

Nice-to-Haves

• Prior work on cooperative perception, vision-language models, or compression algorithms.
• Experience with robotics, autonomous vehicles, and multi-agent AI.

 

The VUB wants to be a reflection of the society where everyone's talent is valued, regardless of gender, ag