Julien Trocmé

Led product development of an AI-powered aura analysis experience from R&D to commercial launch, coordinating external vendors and owning the product roadmap. Delivered €36k in revenue at the pilot store, exceeding the target by 240%.

Built and shipped a toxicity detection model achieving 99% F1-score across 500K+ messages, informing platform moderation decisions. Benchmarked leading NLP/LLM architectures to guide the technology roadmap.

Built a predictive churn model using XGBoost and Random Forest in R, identifying key churn drivers. Designed Power BI dashboards to track KPIs and support data-driven decision-making.

Applied deep learning techniques to object detection, building a computer vision model for automated wine bottle recognition.

Pursued a Master's degree in Computer Science with a focus on Artificial Intelligence as part of a dual degree program.

Earned an Engineering Degree (Diplôme d'Ingénieur) in Computer Science and Statistics.

Completed a DUT in Statistics and Business Informatics.