Automatic document classification supported by Artificial Intelligence (Internship/ Diploma Thesis)

  • ELCA
  • Lausanne, VD, Switzerland
  • 25/09/2020
Full time Data Science Data Analytics Big Data Data Management Statistics

Job Description


Have you ever dreamt of building something new? Envisioning a product, prototyping it, testing the ideas against end users, distilling features, drawing a solution architecture, interacting with marketing and UX designers, working with key users, crafting a solution slowly and carefully and making it happen. A lot of excitement and a lot of challenges too.

Activities: Contribute to the development of a module / web service allowing interaction with large scaled documents repositories. Refine the necessary learning module and processes providing scenarios adapted to different businesses and industries. Work on the interoperability of the developed solution allowing usage in heterogenous contexts. Share findings and ideas to receive the feedback from subject matter experts. Implement the solution using modern technologies.

What you will learn: depending on your skills and profile, you will contribute to and learn about: product design, requirement gathering, machine learning strategies in business scenarios, reviews and demos. By being confronted with early market reality and heterogenous end user maturity levels you’ll develop precious skills for future successful professional interactions.

Keywords: Enterprise Content Management, AI, enterprise integration, product development, front frameworks, document management, taxonomy and classification.

In this role


The objectives of this project are:

  • Integrate ELCA’s NLP processing engine and further develop IA learning model for automatic document analysis and tagging.
  • To develop a minimal viable client application interoperable with ELCA ECM in-house framework called “Mosaic”
  • Build a reusable knowledge base for classifiers on a set of documents for a target industry sector
  • Build front end and web services components to be added to the framework catalog

Possible extension: streaming and “real-time” analysis, deep learning

What we offer

Join our team as intern and you will find a young, dynamic and culturally diverse working environment.

About your profile

knowledge / skills required

  • Design: business analysis, requirement gathering, modelling, domain expert interviews
  • Development: AI Common Framework expertise, Python or similar, Machine learning model’s expertise.
  • Languages: ability to speak and write well in French and English