Assistant Professor (RTDA) in Computer Vision at University of Trento

Position is open

Back to all open positions

The Department of Information Engineering and Computer Science at University of Trento invites applications for a full-time RTDA (Ricercatore a Tempo Determinato di tipo A) position at the Assistant Professor level in the area of Computer Vision, with a particular focus on Vision-Language Models (VLMs) and Multimodal AI. The expected start date is November 2025.

About the Position

We are seeking a highly motivated and promising early-career researcher who is passionate about advancing the field of computer vision and its intersection with natural language processing. The successful candidate will be expected to develop an independent research agenda while actively collaborating with other members of the Department and the broader AI research community.

The candidate will be encouraged to pursue fundamental research in vision-language models and will have the freedom to explore a variety of directions, including but not limited to:

  • Vision-language reasoning
  • Multimodal interpretability and transparency
  • Fairness, bias detection, and mitigation in VLMs
  • Compositionality and generalization in multimodal learning

Requirements

Applicants should have:

  • A Ph.D. in Computer Science or a closely related field
  • A strong research track record in Computer Vision, Multimodal Learning, or related areas
  • At least two publications in top-tier venues such as CVPR, ICCV, ECCV, NeurIPS, ICML, ACL, or EMNLP
  • Excellent communication skills and a collaborative attitude

Responsibilities

  • Conduct high-quality, original research in computer vision and multimodal AI
  • Publish results in top-tier conferences and journals
  • Supervise and mentor graduate students
  • (optional) Teaching at the undergraduate or graduate level
  • Engage with the academic community and participate in departmental activities

What We Offer

The successful candidate will join the Multimedia and Human Understanding Group (https://mhug.disi.unitn.it/), a widely recognized research team in the fields of computer vision and multimedia. MHUG is actively involved in several high-impact international projects on foundation models (e.g., EU projects ELIAS and ELLIOT) and maintains strong collaborations with many international research groups in AI. Based in Trento, a beautiful city in northern Italy, the position offers access to state-of-the-art computational resources, opportunities for interdisciplinary collaboration, and an excellent quality of life.

How to Apply

Applications should be sent to Nicu Sebe (niculae.sebe@unitn.it) and Elisa Ricci (e.ricci@unitn.it) and must include:

  • A cover letter
  • Curriculum vitae with full publication list
  • Names and contact information of at least two referees

The official application process will be available through a web portal shortly.