PROFILE / FIELD NOTES
About
I am a data and AI consultant, agentic entrepreneur, and founder based in Paris. My experience spans production data science at Decathlon and COMPREDICT, data science and data engineering at Alstom, research engineering at VibraTec, and engineering education at INSA Lyon and Mines Rabat.
Current focus
- Agentic systems
- Retrieval
- Time series
- Practical AI tools
Technical strengths
- Python
- Machine learning and deep learning
- Time series
- AWS and Databricks
- MLflow
- Data visualization
Experience
- Co-Founder · LumiereAI ·
- Senior Data Scientist · Decathlon ·
- Designed and productionized a baseline-normalization approach for heterogeneous SKU and store demand series, enabling cross-series learning and comparison, validated through local, Databricks, and backtesting experiments with cold-start behavior safeguarded.
- Spearheaded SHAP-based explainability for production demand forecasting, building reusable global and SKU-store diagnostic workflows, mentoring teammates, and using feature attribution to uncover model behavior and upstream data-quality issues.
- Redesigned forecasting evaluation beyond WAPE and aggregate bias with naive-baseline, relative-error, and directional SignedBias metrics across dbt and Spark monitoring pipelines, so over-forecasting, under-forecasting, volume, and turnover impact can be judged separately.
- Led end-to-end weather feature engineering, from source-data analysis and horizon-aware feature design to model integration, backtesting, monitoring, and stakeholder communication, across multiple markets, product universes, and forecast cutoffs.
- Pioneered internal evaluation of tabular and time-series foundation models, extending the experimentation platform for TabPFN and TabICL and assessing accuracy, interpretability, data requirements, and GPU scalability constraints.
- Built an agent-ready data-science monorepo using reusable agent skills, MCP connectors, and operational documentation, enabling agent-assisted end-to-end experimentation and a reported 2x acceleration in research and development throughput.
- Senior Data Scientist · COMPREDICT ·
- Data Scientist · Data Engineer · Alstom ·
- R&D Engineer · VibraTec ·
Languages & interests
Languages
- French (Native or bilingual)
- Arabic (Native or bilingual)
- English (TOEIC 975/990)
- German (Elementary)
Interests
- Music (Guitar)
- Sports (Rowing and Swimming)
Education
- Engineering degree, Computer Engineering · INSA Lyon ·
- Master of Engineering · Mines Rabat ·
- MP - MPSI · CPGE Taza ·