Airbus · Toulouse, France

• ▸Maintained and evolved a dashboard centralizing QLB customer quality data for the A330 and A350 programs.
• ▸Accelerated the identification of recurring quality non-conformities by developing an LLM-based analysis system for QLBs from final cabin presentations.
• ▸Reduced quality teams' manual search time by designing a RAG pipeline that classifies QLBs from their description, automatically retrieving the applicable acceptance criteria (reference, page, conditions) and status (acceptable/non-conforming).
• ▸Designed an end-to-end ML pipeline using XGBoost to predict customer presentation dates at the A330/A350 FAL, achieving a MAE of 4.1 days and 87% of predictions within ±7 days, improving team planning and resource allocation.

Blent.ai · Paris, France

• ▸Implemented automated ELT pipelines feeding the Customer Data Platform, integrating 5+ sources.
• ▸Developed Reverse ETL flows for marketing tools such as HubSpot and CustomerIO, enabling the marketing team to target campaigns on customer segments updated daily instead of manually.
• ▸Unified client reporting by building sales and marketing dashboards analyzing customer KPIs for a 5-person team.
• ▸Developed an AI chatbot to assist students on the platform and automated the grading of student projects using a RAG system.
• ▸Consulted and designed an AI MVP for the DGAC to automate the extraction and monthly structuring of data from 300 French aerodromes using an LLM.

3D Smart Factory · Mohammedia, Morocco

• ▸Reduced infrastructure costs by 98% ($85/month to $1.3 per 1,000 requests) by deploying a deep learning model for 3D tooth segmentation via a serverless architecture.
• ▸Delivered an interactive 3D visualization interface for exploring tooth segmentations, integrating 3D libraries.