Postdoc in 3D Perception and Spatial Understanding - DTU Compute

DTU - Technical University of Denmark; Kongens Lyngby; On-site; DKK 470,000 - 580,000; Full time

Job summary

DTU Compute invites applications for a postdoctoral researcher to advance 3D perception and spatial understanding within the Visual Computing Lab, led by Theodora Kontogianni. The role emphasizes independent and collaborative work across international partners, with publication in premier venues and mentoring of students.

The appointment is a full-time, two-year position within the Pioneer Centre for AI ecosystem, offering opportunities to contribute to proposals, seminars, and international

Qualifications

• PhD in computer science, ML, robotics or related field.
• Strong publication record in top CV/ML venues.
• Background in 3D perception and spatial understanding.
• Proficient in Python and/or C++.
• Experience with PyTorch and Linux tooling.

Responsibilities

• Conduct independent and collaborative research on 3D perception and spatial understanding.
• Publish findings at top conferences and journals (e.g., CVPR, ICCV, ECCV, NeurIPS, ICML).
• Mentor PhD, MSc, and BSc students in related research areas.
• Contribute to development of research proposals and grants.
• Present research at international conferences and workshops.
• Manage your own academic research and administrative duties, including project coordination.

Skills

Python

C++

PyTorch

Linux

Git

Conda

Docker

Deep learning

3D perception

Research leadership

Education

PhD in CS/EE/Math or related

Tools

Docker

Git

Conda

Job description

Job Description

DTU Compute and the Pioneer Centre for AI are excited to offer a Postdoc position for a talented and motivated researcher to join our lab at DTU led by Theodora Kontogianni.

Responsibilities and Qualifications

The primary goal of this position is to push the boundaries of 3D perception and spatial understanding. The overarching mission of our research lab is to develop intelligent systems that can perceive, interpret, and reason about 3D environments across a wide range of impactful applications. The group’s main focus is advancing spatial AI, aiming to create systems that can build rich representations of their surroundings and support downstream tasks such as navigation, interaction, and decision‑making.

We are particularly interested in candidates who want to explore one or more of the following research areas: 3D scene understanding, spatial reasoning, semantic and instance‑level perception, multi‑modal learning for spatial representations, and foundation models for 3D environments. You will be a vital part of the Visual Computing Lab, working alongside Theodora Kontogianni. Collaboration with academic partners, locally and internationally, will be a core part of the role.

Your primary tasks will be to:

• Conducting independent and collaborative research on 3D perception and spatial understanding, including scene recognition, spatial reasoning, and learning‑based methods for interpreting complex 3D environments.
• Publishing research findings in leading international conferences and journals (e.g., CVPR, ICCV, ECCV, NeurIPS, ICML).
• Mentoring and co‑supervising PhD, MSc, and BSc students in related research areas.
• Contributing to the development of research proposals and grant applications.
• Presenting research at international conferences and workshops.
• Managing your own academic research and administrative duties, including project coordination and ensuring deliverables meet deadlines.

Selection Criteria

• A PhD degree in computer science, electrical engineering, mathematics, or a closely related field with a focus on computer vision, machine learning, or robotics.
• A strong publication record in top-tier computer vision and/or machine learning venues (e.g., CVPR, ICCV, ECCV, NeurIPS, ICML, ICLR, ICRA, WACV).
• A strong background in 3D perception and spatial understanding, including areas such as 3D scene understanding, spatial reasoning, point cloud processing, multi‑view learning, or neural scene representations.
• Proven software and debugging skills in Python and/or C++.
• Experience with deep learning frameworks such as PyTorch.
• Experience in Linux and development tools such as git, conda, or docker.
• Ability to conduct independent research and lead collaborative projects.
• Excellent communication skills and ability to work on interdisciplinary teams.
• Experience with embodied AI, augmented reality, or autonomous navigation is a plus.

As a formal qualification, you must hold a PhD degree (or equivalent).

We offer

DTU is a leading technical university globally recognized for the excellence of its research, education, innovation and scientific advice. We offer a rewarding and challenging job in an international environment. We strive for academic excellence in an environment characterized by collegial respect and academic freedom tempered by responsibility.

Salary and terms of employment

The appointment will be based on the collective agreement with the Danish Confederation of Professional Associations. In addition, supplements can be negotiated in accordance with DTU’s salary structure for scientific staff: www.inside.dtu.dk/en/human-resources/during-employment/salary/salary-structures.

Preferred starting date is 1 November 2026 or according to mutual agreement. The position is a full-time position, and the period of employment is 2 years.

You can read more about career paths at DTU here.

Further information

Further information may be obtained from Theodora Kontogianni ( [e-mail] ).

You can read more about DTU Compute – Visual Computing at https://orbit.dtu.dk/en/organisations/visual-computing and previous research at https://theodorakontogianni.github.io/ and https://scholar.google.com/citations?user=QVJIkWwAAAAJ.

If you are applying from abroad, you may find useful information on working in Denmark and at DTU at DTU – Moving to Denmark.

Equal Opportunity Statement

All interested candidates irrespective of age, gender, disability, race, religion or ethnic background are encouraged to apply. As DTU works with research in critical technology, which is subject to special rules for security and export control, open‑source background checks may be conducted on qualified candidates for the position.

Visual Computing at DTU Compute

The Visual Computing section at DTU Compute leads research in extracting information from images through cutting‑edge methods in image analysis and computer vision. This work focuses on areas such as Medical Image Analysis, Computer Vision, and 3D Microstructure Analysis, where vision‑based technologies play a key role in solving real‑world problems. The lab’s contributions in these fields have not only advanced the theoretical foundations of visual computing but also resulted in practical innovations, including the founding of several startups by former researchers.

Pioneer Centre for AI

The Pioneer Centre for Artificial Intelligence, established in 2021, is Denmark’s largest AI research centre. Hosted by the University of Copenhagen, it collaborates with leading institutions such as the Technical University of Denmark (DTU), Aalborg University, Aarhus University, and the IT University of Copenhagen. With over 507 researchers and 60 workspaces, the centre focuses on foundational and applied AI research that addresses societal challenges across ten areas, including robotics, healthcare, climate, and economic growth.

DTU Compute

DTU Compute – Department of Mathematics and Computer Science – is an internationally recognised academic environment with over 400 employees and 10 research sections. We broadly cover digital technologies within mathematics, data science, computer science, and computer engineering, including artificial intelligence (AI), machine learning, internet of things (IoT), chip design, cybersecurity, human‑computer interaction, social networks, fairness, and data ethics. Our research is rooted in basic research and centres on mathematical models of the physical and virtual world, as a basis for the analysis, design, and implementation of complex systems. We focus on ensuring that our research results contribute to creating a better society by supporting areas such as health, green transition, energy supply, and life science. We collaborate with universities, public and private organisations, and companies in Denmark and abroad, and through DTU’s startup ecosystem, we encourage innovation and entrepreneurship. We have a strong ethical, human, and sustainable approach that ensures integrity in our work. Therefore, we strive for and take responsibility for driving the democratization of digital technologies, so that everyone has the opportunity to actively participate in the development, and we ensure a continued open, democratic, and inclusive society for the benefit of all. At DTU Compute, we value diversity, inclusion, and a flexible work‑life balance. Read more about us at www.compute.dtu.dk.

DTU – For the benefit of society since 1829

DTU is one of Europe’s leading elite technical universities. Through research and education at an international top level, we create solutions to the major societal challenges of our time and help secure Europe’s global leadership in sustainable technological development. Since Hans Christian Ørsted founded DTU almost 200 years ago, our mission has remained the same: We develop and create value through the natural and technical sciences for the benefit of society. DTU has 13,800 students, 1,600 PhD students, and 6,500 employees. We work in an international environment and have an inclusive, stimulating, and informal work culture. DTU has campuses in all parts of Denmark and in Greenland and collaborates with the best universities around the world.