Medior Data Scientist (Lisbon)

We are looking for someone with experience that is capable of taking over a specific project and research and implement a workable solution on a production environment.


We have a big data set of retail product information, and we continuously strive to provide additional information on top of the data we collect. This means using Machine Learning for doing things like:

  • Matching 2 products with slightly different information (but that are actually the same one)
  • Standardize different retailers categories, measures and specifications into a standard tree.
  • Use product image to extract additional information from products (packaging, colors for example).
  • Automatically extracting data from websites.


  • Proven Data Scientist with at least 3 years of professional experience in Natural Language Processing(NLP) and Machine learning
  • Experience in using one or more of the following: NumPy, pandas, SciPy, Scikit-Learn, NLTK, SpaCy, TensorFlow, Keras, Pytorch
  • Deep Learning a big plus
  • Knowledge of the AWS stack nice to have.
  • Fluency of Dutch language a nice thing to have.
  • Experience taking ambiguous problem statements through to delivered products.
  • Curiosity and enthusiasm, and a love for teaching and learning
  • Based in Lisbon (Portugal) or willing to relocate

What can Daltix offer you?

  • Daltix’ offers a competitive wage (including various benefits etc) and a young, dynamic and international (we have offices in Belgium and Portugal) atmosphere to work in.
  • When you start working at Daltix, you will get a deep dive experience. You learn all you need to know about us, our journey, your future colleagues, the tools we work with, etc.
  • Going beyond, is coded in our company DNA. As soon as you start working, we expect a hands-on approach, with an entrepreneurial mentality.
  • You will also be able to participate in relevant trainings to stay at the top of this field.

About Tech Stack

Daltix is actively investing in building up a data science team which is tasked to work on various challenges such as:

  • Matching similar products across different retailers.
  • Automatic categorization (classification) of products.
  • Automatic interpretation of websites.

For this it is using technologies such as Pytorch,, spaCy.

Besides this Daltix is analysing data in order to help big retailers such as Makro & Lidl or suppliers such as Unilever to stay competitive in terms of pricing, promotions and assortment.

Python (pandas, Pyspark) is also used here as it is currently the most suited language (sorry R) for data analysis & science.