PhD in Visual Dialogues & Multimodal AI

Danmarks Tekniske Universitet; Ørsted; On-site; DKK 269,000 - 359,000; Full time

Benefits offered by this job

Fully funded PhD (3 years)

Job summary

DTU Compute – Department of Applied Mathematics and Computer Science in Denmark invites applications for a fully funded 3-year PhD in Visual Computing. You will conduct research at the intersection of computer vision, multimodal AI, and human-AI interaction, publishing at top venues and collaborating internationally.

The PhD stipend is aligned with the Danish collective agreement; start in Fall 2026. Help build AI that communicates visually and engage in teaching as a TA at DTU.

Qualifications

• Two-year master's degree (120 ECTS) or equivalent in CS/informatics/AI-related field.
• Proven experience in Python and deep learning frameworks.
• Strong motivation, innovative mindset, and English communication skills.

Responsibilities

• Develop state-of-the-art computer vision and multimodal AI models for visual dialogues.
• Build and curate datasets to train and evaluate models.
• Publish research at top venues (CVPR, ICCV, ECCV) and present findings.
• Spend a few months abroad and contribute as a teaching assistant at DTU.

Skills

Python

Deep learning frameworks

English communication

High motivation & innovation

Computer vision (plus)

Education

Two-year master's degree or equivalent

Job description

DTU Compute – Department of Applied Mathematics and Computer Science in Denmark invites applications for a fully funded 3-year PhD in Visual Computing. You will conduct research at the intersection of computer vision, multimodal AI, and human-AI interaction, publishing at top venues and collaborating internationally.

The PhD stipend is aligned with the Danish collective agreement; start in Fall 2026. Help build AI that communicates visually and engage in teaching as a TA at DTU.