Postdoctoral Research Position for Administrative Document Understanding

July 10, 2020 at 2:29 pm by

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.

The Intelligent Reading Systems (IRS) group counts with more than 20 years of research and technology transfer experience in computer vision systems for extracting and interpreting written (textual or symbolic) information in images. The group is an international leader in scene text understanding, document image analysis, graphics recognition, handwritten recognition, musical scores understanding, and human-document interaction. It is a recognised consolidated group of the Catalan research systems since 2005. With more than 30 members, the group is one of the biggest ones worldwide in its field. The members of the group have produced more than 300 scientific publications and have participated in a large number of European and national research projects, as well as numerous technology transfer activities.


The IRS research group seeks applications to fill a postdoctoral applied research position focused on the development of document analysis algorithms applied to administrative documents such as invoices, receipts, forms, contracts, etc. The final goal is to move towards document understanding by means of extracting, in a structured way, relevant and semantic information from administrative documents.

Experiments will be carried both on large scale public datasets as well as in-house private datasets coming from the different industrial projects of the IRS group. The successful candidate will work in a research environment, closely collaborating with different companies with whom we have industrial tech transfer projects on the field of administrative documents.

Main duties

  • Design and develop novel information extraction and document understanding deep learning algorithms. Run benchmarking tests with the available datasets,
  • research on graph neural networks for representing and extracting relevant information from document images,
  • periodically reporting of the different project advances with different industrial partners.


  • PhD in computer science specialized in machine learning and, in particular, document image analysis,
  • 2+ years of postdoctoral experience, good publication record,
  • strong programming skills in Python and/or C++,
  • knowledge and demonstrable experience with Deep Learning frameworks (Tensorflow, Pytorch, …) and image analysis packages (OpenCV, PIL),
  • experience working in Linux computing environments,
  • experience in machine learning, GPU programming, distributed data processing systems or high performance computing will be a plus,
  • able to work independently as well as within an interdisciplinary team,
  • fluent in English. Good communication skills.

Type of contract

  • 2 years’ PostDoctoral contract, salary according to the CVC labor categories

Application process

If interested, please send your CV, a motivation letter and 2 reference letters through this website, indicating offer code 17042020_POSTDOC-ADU. (IMPORTANT: All documents should be together in one document in order to be able to upload the file)