ph3POSTDOC POSITION IN MULTIMODAL FOUNDATION MODELS FOR DOCUMENT UNDERSTANDING /h3 pCall reference: _MDU /p pWe are seeking apostdocto 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 Understanding” (Mu Doc U), financed by the Spanish Ministry of Science. /p pThe successful candidate is expected to participate in large‑scale training efforts, research on multimodal pre‑training and finetuning methods, and applications on the specific use case of Document Understanding. /p h3KEY DUTIES /h3 pLead and contribute to specific Work Packages (WPs) within the project, ensuring timely delivery of objectives and nduct cutting‑edge research on multimodal large language models (LLMs), and manage the publication of research findings in top‑tier conferences and journals. /p pPrepare and submit proposals for high‑performance computing (HPC) resources and manage allocated compute efficiently. /p pOptimize training pipelines for scalability and ntribute to group mentoring activities such as reading groups or internal seminars. /p pActively collaborate with internal group members and external project partners.



/p h3CANDIDATE’S PROFILE /h3 pThe candidate should possess a Ph D in machine learning or computer vision, or be in the final stage of their Ph D with a scheduled or imminent thesis defense. A strong publication record is required. We are looking for candidates who have publications in top conferences like ICDAR, CVPR, ECCV, ICCV, AAAI, Neur IPS. /p pThe candidate should have a strong background in Large Language Models and experience in the document image analysis field. Experience in industry will be considered a strong asset. /p pThe applicant is expected to be fluent in both oral and written communication in English. They should work well in a team while demonstrating initiative and independence. The candidate is expected to co‑supervise Ph D. /p pGross annual salary: €30,000 /p pStarting date: July or September 2026 /p h3ABOUT CVC /h3 pThe selected candidate will work in the Computer Vision Centre (CVC) in Barcelona, a research institute comprising more than 150 researchers and support staff, dedicated to computer vision research and knowledge transfer. /p h3LOCATION /h3 pBellaterra, Kingdom Of Spain, ES /p /p #J-18808-Ljbffr

📌 Postdoc Position In Multimodal Foundation Models For Document Understanding (Barcelona)
🏢 Centre De Visio Per Computador
📍 Barcelona