Postdoctoral Research Position for Administrative Document Understanding
Purpose 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.
- 2 years’ PostDoctoral contract, salary according to the CVC labor categories
SHARE ON
