Soufiane Lemrabet

– Developing and maintaining scalable data pipelines within the Palantir platform. – Designing and optimizing Big Data workflows using Apache Spark and Python. – Automating data processing and quality control workflows. – Collaborating with Data Science teams to provide reliable and reusable datasets. – Contributing to the optimization of data infrastructure for scalability and performance.

– Worked on a Synthetic Data Generation project aimed at creating artificial datasets that mimic real-world data while preserving privacy and security. – Applied statistical and Machine Learning techniques to generate realistic synthetic data for testing and analysis without exposing sensitive information. – Evaluated the similarity between real and synthetic data using relevant metrics to ensure quality and usability. – Contributed to documentation and integration of the tool within the internal testing environment.

– Studied and implemented Deep Learning (GANs) methods to generate correlation matrices in the financial domain. – Conducted comparative analysis of different GAN architectures to produce reliable samples. – Validated results against economic and statistical criteria.