Pablo S.

I am currently developing a Python-based library for advanced optimisation called Lurtis EoE. This library integrates ML techniques (XGBoost, DecisionTtree, Random Forest, multi-layer perceptron and linear models) with complex metaheuristic optimisation algorithms (genetic algorithms, evolutive algorithms as DE or SHADE, local search algorithms as MTS or L_BFGS_B, among others). Lurtis EoE is also compatible with a cloud-based deployment using AWS, GC, Azure or Kubernetes, and relies on a tailored-made MapReduce approach for the training of the models and the execution of the objective function that is being optimised.

I have also had the opportunity of leading a team for creating a web-based data analytics tool at Lurtis working for Arix Technologies although this project grew and diverged from Lurtis EoE and my thesis. In my previous experiences, I have worked with Python and PySpark creating models for predictive maintenance for Airbus at Capgemini. That included big data analysis, data visualisation using Matplotlib, and the creation of a desktop program in Python and Cython for visualising data when an incident happened.

Finally, during my time as a Teaching Assistant time at the University, I dealt with CI/CD in Azure, AWS and GC, as well as with SQL, although I rapidly transited to NoSQL databases.