POSTDOC POSITION IN MULTIMODAL FOUNDATION MODELS FOR DOCUMENT UNDERSTANDING:
Call reference: 20260619_MDU

Closing date: 28/06/2026

We are seeking a postdoc to join the Vision, Language and Reading group at the Computer Vision Center (CVC), in Barcelona, Spain.

The position is initially for 1 year and linked to the project “Multimodal LLMs for Document Undestanding” (MuDocU), financed by the Spanish Ministry of Science.
- Proyecto PID2023-146426NB-100 financiado por MICIU/AEI /10.13039/501100011033 y por FEDER, UE._

KEY DUTIES
- Lead and contribute to specific Work Packages (WPs) within the project, ensuring timely delivery of objectives and milestones.
- Conduct cutting-edge research on multimodal large language models (LLMs), and manage the publication of research findings in top-tier conferences and journals
- Prepare and submit proposals for high-performance computing (HPC) resources and manage allocated compute efficiently.
- Optimize training pipelines for scalability and reproducibility.




- Contribute to group mentoring activities such as reading groups or internal seminars.
- Actively collaborate with internal group members and external project partners

CANDIDATE ’S PROFILE

CONDITIONS
- Location: Computer Vision Center (Campus Universitat Autònoma de Barcelona)
- Gross annual salary: 30.000 €
- Starting date: July or September 2026

THE COMPUTER VISION CENTER

Barcelona is a vibrant city and an important Artificial Intelligence hub. The high quality of life is combined with an open and international looking character of the city. Barcelona is very well connected by air, sea and ground transportation. The region of Catalonia boosts its own AI strategy, in which the CVC is a key player.

APPLICATION PROCESS

OTM-R Principles for Recruitment Processes

CVC is committed to the principles of Open, Transparent and Merit-based Recruitment (OTM-R) across all its recruitment processes. In 2015, we were awarded the HR Excellence in Research seal by the European Co

📌 Postdoc Position Inmultimodal Foundation Models Fordocument Understanding (Bellaterra)
🏢 Centre De Visio Per Computador
📍 Bellaterra