PhD Candidate in Computer Vision and Multimodal AI Interaction

Job summary

This position offers a fully funded 3-year PhD opportunity focused on developing AI systems capable of engaging in visual dialogues, enhancing human-AI communication beyond text. The role involves conducting innovative research in computer vision and multimodal AI, with the aim of creating models that interpret and generate visual responses.

Qualifications

• A two-year master’s degree or equivalent in computer science, informatics, computer engineering, applied mathematics, or a related field.
• Proven experience in Python programming.
• Hands-on experience with deep learning frameworks.
• High motivation and innovative mindset.
• Experience in computer vision is advantageous.
• Excellent written and verbal communication skills in English.

Responsibilities

• Develop advanced computer vision and multimodal AI models for visual dialogues.
• Build and curate datasets for model training and evaluation.
• Publish and present research findings at leading conferences (e.g., CVPR, ICCV, ECCV).
• Participate in teaching as a teaching assistant at the university.
• Spend several months abroad during the PhD program.

Education

Candidates must hold a master’s degree or equivalent prior to starting the PhD program.

Tools

• Python
• Deep learning frameworks