Postdoctoral positions for the Document Analysis research group at Computer Vision Center 

Job Reference: 20250731_DAG 

Closing date: open until the candidates are selected 

About CVC 

The Computer Vision Center (CVC) is a non-profit research center established in 1995 by the Generalitat de Catalunya and the Universitat Autònoma de Barcelona (UAB). Its mission is to carry out cutting-edge research that has the highest international impact in the field of computer vision. It also promotes the transference of knowledge to industry and society.  

Computer vision is an exciting research area and an omnipresent technology, essentially empowering machines with the sense of vision. The CVC is a successful marriage between knowledge and innovation. In addition to our cutting-edge scientific achievements, we have established lasting ties with industrial partners and created several spin-off companies. 

Context and Mission 

The Document Analysis group is looking for Postdoctoral researchers to collaborate on handwriting recognition. The objective is to explore methodologies suitable for historical documents in low resource scenarios (when training data is scarce), such as self-supervised learning, continual learning, synthetic data generation, etc. Architectures can be based on deep learning models and/or Spiking Neural Networks. 

The successful candidates will work in close collaboration with researchers of the Document Analysis research group.  

This position is linked to the project “DESCRYPT: Echoes of History: Analysis and Decipherment of Historical Writings”, financed by the Riksbankens Jubileumsfond. More info at: https://www.descrypt.org/  

Key Duties 

• The candidates will have to perform research on the topic of the project 
• The candidates are expected to present results at top conferences or journals in the field 

Requirements:  

• Education 
  • PhD in Computer Science 
• Essential Knowledge and Professional Experience 
  • Previous experience in deep learning (e.g. Recurrent Neural Networks, Transformer Networks, Generative Adversarial Networks, etc.). 
  • Previous experience in the field of document image recognition/understanding 
  • Good programming skills using Pytorch, Tensorflow, or similar frameworks. 
• Additional Knowledge and Professional Experience 
  • Professional experience in scientific publications in relevant forums 
  • Previous experience in Spiking Neural Networks 
• Competences 
  • Fluency in spoken and written English 
  • Ability to think creatively, work independently and make decisions. 
  • Ability to take initiative, prioritize and work under set deadlines and pressure 
  • The candidate must be an effective communicator, multitask, and work well on collaborative and interdisciplinary designs. 

Conditions  

• The position will be located at Computer Vision Center (Campus Universitat Autònoma de Barcelona). 
• We offer a full-time contract (37.5h/week) temporary contract], a good environment, flexible working hours 
• Duration: 1 year (which could be extended up to 3 years) 
• Salary in accordance with qualifications and experience of the candidate and to CVCs salary regulations. 
• Starting date: As soon as possible 

Applications procedure and process 

All applications must be sent through the online form, indicating the following offer code: 20250731_DAG 

Application Deadline:  

The vacancies will remain open until suitable candidates have been hired. Applications will be regularly reviewed, and potential candidates will be contacted. 

OTM-R principles for selection processes 

The CVC is committed to Open Transparent and Merit-based Recruitment (OTM-R) for any potential candidate in all our processes. In 2015 we received the Human Resources Strategy for Researchers (HRS4R) award. Through an extensive and continuous process, we improve the conditions and opportunities at CVC. With these actions, the CVC is committed to the principles of the European Charter for Researchers, as well as the Code of Conduct for the Recruitment of Researchers. 

For more information follow this link