Hi There 👋, I’m Catherine Gitau, currently working as an NLP Engineer at ProtoCX training multilingual chatbots for contact centers.

I recently completed my Masters’ in Machine Intelligence at the African Institute for Mathematical Sciences(AIMS) under the African Masters’ in Machine Intelligence (AMMI) program.

While pursuing my Masters’ I joined the DSFSI Research Group where I worked on textual data augmentation techniques for low-resource Machine Translation supervised by Dr. Vukosi Marivate.

We also received a research grant by Mozilla to work on a Machine Translation platform for African Languages that’s free and open sourced. Feel free to play around with the platform here and provide feedback on the translations which will help in improving the translation models.

I enjoy finding and building solutions to practical real-life problems using data. I am really not sure which title to give myself; part data scientist part machine learning engineer and part applied research scientist 🤷‍♀.

My current goal is to get acquainted with Machine Learning Operations(MLOps) so that I can build end-to-end machine learning systems that are able to serve people at scale.

My current interests are in Natural Language Processing for low-resourced languages, understanding Graph Networks and recommendation systems. I’ll try as much as possible to write about my learnings on these topics and more!


Feb 2020 - Present: NLP Engineer @ ProtoCX

Sept 2020 - Present: Research Fellow @ DSFSI Research Group(Machine Translation Service for African Languages)

Apr 2018 - June 2021: Data Scientist @ Africa’s Talking(Analytics, CLV)

Jan 2019 - Aug 2019: Deep Learning Indaba(Organizing Commitee)

Oct 2017 - April 2018: Junior Data Scientist @ Ongair Limited

June 2017 - Oct 2017: Data Science Intern @ Brave Venture Labs