Assistant/Associate Professor in Video Processing and Animation with Deep Learning - 3 years fi[...]

Karlstad University; Gif-sur-Yvette; Sur place; EUR 40 000 - 60 000; Plein temps

Résumé du poste

A French engineering school is seeking an Assistant/Associate Professor in Video Processing and Animation with Deep Learning for a 3-year fixed-term contract. The role involves designing teaching programs, conducting research in AI-driven animation, and developing partnerships. Candidates must have a PhD and fluency in English, with preferences for specializations in image processing, generative AI, and video compression. Benefits include remote working options, paid leave, and a supportive integration program.

Prestations

1 to 3 days of remote working

49 days of paid leave

Mutual insurance & provident fund

Qualifications

• PhD required in video processing, animation, or a related field.
• Fluent in English.
• Expertise in deep learning applications in digital media.

Responsabilités

• Design and implement teaching programs in video processing and animation.
• Conduct research in video processing and deep learning.
• Develop partnerships and collaborations.

Connaissances

Image processing with deep learning

Generative AI and multimodality

Image and Video compression pipelines

Self-supervised learning

Development at multiple levels of abstraction

Managing open-source projects

Formation

PhD in relevant field

Description du poste

Assistant/Associate Professor in Video Processing and Animation with Deep Learning - 3 years fixed-term contract

Télécom Paris, an international multidisciplinary center for education, research, and innovation, is a leader in the digital world.

The rise of artificial intelligence and particularly of deep learning techniques has profoundly impacted research for all data modalities: audio, images, videos, text, 3D, etc. Indeed, this call aims at reinforcing the equipe Multimedia in one of the following areas, having a strong accent to AI.

Animation is a dynamic and evolving field where artificial intelligence is driving transformative advancements, particularly in automated motion synthesis, real-time rendering, and expressive character generation. Modern techniques, such as neural motion models and physics-based simulation, enable the creation of lifelike animations with reduced manual intervention, benefiting industries like gaming, film, and virtual production. AI-powered tools can interpolate keyframes, enhance lip-syncing for dubbed content, or even generate entirely new animations from textual or audio inputs using multimodal foundation models. Additionally, innovations in procedural animation and 3D Gaussian splatting allow for more efficient scene reconstruction and dynamic asset generation, critical for immersive AR/VR experiences. As the demand for personalized and interactive digital content grows, research at the intersection of AI and animation holds immense potential to redefine creativity, production pipelines, and user engagement.

Another critical area is neural network-based video processing, which includes specialized models for video restoration, artifact removal, and enhancement of low-quality or historical footage. Additionally, secure deepfake technologies present opportunities for verified digital avatars and innovative applications in entertainment, requiring robust and ethically aligned solutions.

3D Gaussian Splatting represents a transformative approach for fast and accurate 3D scene reconstruction, with significant implications for augmented reality (AR), virtual reality (VR), and industrial simulations. Research in this domain may lead to patented methods for integrating this technique into interactive tools and industrial pipelines, enabling real-time 3D modeling and immersive experiences.

Finally, video-centric foundation models for multimodal applications open new possibilities in AI-driven content generation, such as creating or modifying video based on textual or audio inputs. These technologies also support automated video summarization, which has broad utility across media, education, and surveillance industries, enhancing accessibility and information processing.

Your main tasks will be to:
- Participate in the design and implementation of teaching programs in your scientific field
- Conduct research in your scientific field
- Participate in the development of partnerships, collaborations and contractual relationships in your scientific field

Job requirements

To succeed in this role, you have a PhD and you are fluent in English.

The position is open to all candidates working in video processing/animation with Deep Learning or 3D processing with Deep Learning.

Expertise in the following areas will be preferred:

• Image processing with deep learning
• Generative AI and multimodality
• Image and Video compression pipelines (both traditional and AI-based)
• Self-supervised, sequential learning, transfer learning, domain adaptation
• Development at multiple levels of abstraction
• Expertise in managing open-source projects
• Scientific excellence: Renowned laboratories (LTCI, i3, CREST), cutting-edge equipment, and international recognition.
• Multidisciplinarity: Working at the intersection of all areas of digital technology.
• Personalized support: Integration program, dedicated training, exchange seminars, and paid study trips.
• Benefits: 1 to 3 days of remote working and nomadic working possible, 49 days of paid leave/RTT, mutual insurance & provident fund, etc.

To apply, please send your file before March 15, 2026:

• Detailed curriculum vitae (max 2 pages)
• Covering letter
• Activity report (table of activities) on research (supervision, problems, etc.), teaching (title, volume, etc.) and collective tasks (max 4 pages)
• Teaching description (summary of activities, a brief plan for integration into teaching at university and continuing education) (max 4 pages)
• Research description (summary and results of activities, a brief plan for integration into research) (max 4 pages)
• Copy of the 3 best publications, list of publications
• Names and contact details of 2 qualified references

The selection process takes place in 4 steps:

• Exchange with the host team to establish a list of shortlisted candidate
• Preliminary interview with Human Resources
• Hearing by the recruitment committee and ranking of the selected candidates
• Final interview with the Director of Télécom Paris

Our recruitment is based on skills, without distinction of origin, age, gender identity, or sexual orientation, and all our positions are open to individuals with disabilities.

Job details

Title

Assistant/Associate Professor in Video Processing and Animation with Deep Learning - 3 years fixed-term contract

Published

2026-01-19

2026-03-15 23:59 (Europe/Paris) 2026-03-15 23:59 (CET)

Télécom Paris is a member ofIMT(Institut Mines-Télécom), the leading group of engineering and management schools in France.