Freelancer profile translated to English.
Back to original languageAbout Nolan
AI&ML Engineerspecializing inproduction-readyAI solutions. I have designed and deployed enterprise-scale systems, from RAG chatbots to automated ML pipelines.
In production:
- Deployed RAG chatbot on Google Chat (LangChain, LangGraph, Gemini, GCP, Terraform):13,000 hrs/yearsaved
- ML forecasting pipeline for 64 categories × 8 KPIs (Prophet, Spark, Databricks):+15% accuracy
Deployed projects:
- Multi-agent financial research **agent**: Hybrid RAG on SEC filings, semantic reranking (LangGraph, Qdrant, Azure, Terraform)
- YouTube comment **analyzer**: BERT sentiment, BERTopic topics, LLM summaries, real-time dashboard (Next.js, FastAPI)
- **Full MLOps pipeline**: EfficientNet-B0, Vertex AI Pipelines, Prometheus/Grafana monitoring, GitHub Actions CI/CD
Junior World Champion in freestyle football, 2x French Vice-Champion, Top 15 worldwide. Bringing the rigor of high-level sports to every project.
French
Native or bilingual
English
Fluent
Remote only
Primarily works remotely
Experience
- Decathlon FranceAI & ML EngineerSeptember 2025 - Today (9 months)
- DevelopedDAISI(Decathlon AI Suppliers Information): anAI chatbotdeployed on **Google Chat**, providing instant answers on supplier processes, trained on internal procedures, with escalation capabilities to accountants.
- Estimated impact:13,000 hours/year savedfor the supplier team.
- Developedproduction-ready RAG architecturesusing LangChain, LangGraph, and Vertex AI Vector Search with GCP Cloud Run, Terraform IaC, and24/7 availabilitywith automatedGDPR-compliantdata cleansing and retention policies.
- ImplementedMLflowexperiment tracking, anLLM-as-Judgeevaluation pipeline,Model Armorfor prompt injection protection, andOpenTelemetrydistributed tracing for full observability.
- Decathlon BelgiumData ScientistMay 2025 - September 2025 (4 months)
- Led a strategic Data Science project to industrialize the forecasting of8 key sales KPIs(GMV, items sold) segmented by channel (InStore/OutStore, 1P/3P) for 64 sports categories.
- Built anautomated forecasting pipelineusing Prophet, Apache Spark, and Databricks.
- Improvedforecast accuracy by +15% (MAPE)compared to the previous manual process through rigorous model comparison (Prophet, XGBoost, LightGBM, Chronos-Bolt) andfeature engineering(weather, holidays, lagged features).
- Implementedparallel processingwith joblib and deployed models to theMLflow Model Registryfor **production inference**. Automated exports to Google Sheets for business stakeholders.
Technologies: Prophet, Apache Spark, Databricks, MLflow, AWS S3, Airflow, GitHub Actions, Python - Beobank NV/SAData Analyst/ScientistMay 2023 - September 2023 (4 months)
- Proficient inPython, VerticaPy, SQLand data processing technologies. Developedanalytical dashboardsand reports with Matplotlib forbusiness intelligenceand decision support.
Technologies: Python, SQL, Pandas, NumPy
Recommendations
Be the first to recommend Nolan
Help this freelancer shine by sharing your experience working together.
These freelancer profiles also match your criteria
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
Education
- Engineering Degree - Data Science & Machine LearningJUNIA ISEN2026Diplôme d'Ingénieur
- Preparatory Classes2023Préparatoires