Decathlon AI

Transforming Data into Intelligent Solutions

AI & ML Engineer specializing in production-ready ML pipelines, RAG architectures, and LLM agents.
I transform complex business challenges into robust, industrialized AI solutions.
Available for freelance AI/ML projects.

About – Nolan Cacheux

Mistral AI Worldwide Hackathon - London 2026 - Ecotopia

Selected among 7,000+ global applicants. Built an interactive political simulation powered by fine-tuned Mistral SLMs. 4 models fine-tuned via QLoRA in under 10 minutes each — our 8B outperforms Mistral Large on structured output at 10x lower latency.

View details

DAISI - AI Assistant for Supplier Processes

Production-level enterprise GenAI chatbot for Decathlon Finance, saving 13,000 hours/year for the suppliers team. Built with LangGraph, Google Gemini, and RAG architecture on GCP infrastructure.

View details

Belgium Sports Sales Forecast

Production ML pipeline for predicting 8 sales KPIs across 64 sports categories using Prophet, PySpark, and Databricks with MLflow model registry.

View details

RAG Equity Research Agent

AI-powered autonomous quantitative analyst using LangGraph orchestration, hybrid RAG for SEC filings analysis, and real-time market data. Deployed on Azure Container Apps with Telegram bot interface.

View details

AI Product Photo Detector

MLOps pipeline for detecting AI-generated product images using EfficientNet-B0. Features real-time FastAPI inference, MLflow experiment tracking, data drift monitoring, and Docker Compose deployment. Trained on the CIFAKE dataset (CIFAR-10 real vs Stable Diffusion AI-generated).

View details