À propos de Thomas
- Nettoyage et traitement des données brutes
- Analyses statistiques avancées pour révéler des opportunités
- Conception de tableaux de bord interactifs (Power BI, Tableau, Looker)
- Rédaction de rapports clairs avec recommandations opérationnelles
- Modèles ML (classification, régression, séries temporelles)
- Feature engineering, tuning, et optimisation des performances
- LLMs
- Intégration de modèles en production et monitoring (Databricks, AWS…)
- Scripts pour automatisation, manipulation de données, APIs, scraping
- Développement web
Français
Bilingue ou natif
Anglais
Bilingue ou natif
Espagnol
Capacité professionnelle limitée
Expériences
- EkimetricsData Science and Artificial Intelligence ConsultantCONSEIL & AUDITseptembre 2022 - septembre 2024 (2 ans)Paris, FranceAt Ekimetrics, I partnered with major clients in retail, automotive, and luxury to design and implement impactful projects. My deliveries were focused on :
- Data Science : time series forecasting, churn prediction, customer segmentation, causality, regression
- Data Analytics : design and implementation of dashboards using Figma, Power BI, Tableau and Looker Studio
- Marketing Mix Optimization : Modeling of the marketing mix of big companies in order to optimization their media budget through a data science approach
- Generative AI : Working on LLMs prompt engineering, LLms integration and fine-tuning
- CHU de LilleDeep Learning ScientistSANTÉ & BIEN-ÊTREseptembre 2021 - février 2022 (5 mois)Lille, FranceIn parallel with my final-year at the École Centrale, I joined a research teamfrom the Hospital University Center. The project I worked on aimed at exploringthe potential improvement of auto-immune illness diagnostic thanks to a deeplearning approach.The main challenges of this project was :1. Data Cleaning for Deep Learning use : in order to be able to train deep neural networks I had to standardize a 60 000 images database gathered over 5 years. It was a good exercice to get used to computer vision basic manipulations.2. Choose the right network : my aim was to create an algorithm that could help doctor to double check their diagnostics. I benchmarked several state-of-the-art algorithms (AlexNet, ResNet, VGG, GANs) and tried different approches to maximize the recall (True Positive Rate).
- MeeroComputer Vision ResearcherEDITION DE LOGICIELSavril 2022 - septembre 2022 (5 mois)Paris, FranceWithin the Research Squad of the R&D department I explored many different ways to perform image restoration (blur removal, noise removal and compression artifacts removal). I studied state-of-the-art models such as Generative Adversarial Models, Transformers and Deep Neural Networks. On the other hand I also implemented and train my own architectures to try to achieve good restoration and image quality assessment performances.
Recommandations
Soyez le premier à recommander Thomas
Contribuez à la réussite de ce freelance en partageant votre expérience de collaboration avec lui.
Ces profils de freelance correspondent également à vos critères
Agatha Frydrych
Backend Java Software Engineer
4.7
(3)
2
Baptiste Duhen
Fullstack developer
4.6
(4)
5
Amed Hamou
Senior Lead Developer
4
(2)
7
Audrey Champion
Web developer
4.3
(3)
4
Formations
- Diplôme d'Ingénieur de l'École CentraleÉcole Centrale de Lille2022Spécialisation en Sciences des Données et Intelligence Artificielle