/ engineering
English lessons →
FR EN
PDF portfolio
Menu
PDF portfolio
English lessons →
FR EN

Projects

Fifteen professional projects, from most recent to oldest, then a personal project. Each row opens on the context, my role and the key deliverables.

Download the portfolio (PDF) Career
Legend
  • Groupe Flow Line
  • Inetum
  • Atos
  • Internships
  • Personal project

15 projects · most recent first

Detailed projects

Context · My role · Key deliverables

01 Supply chain AI platform Groupe Flow Line, Lyon Since January 2026 AI platform plugged into clients' ERP (reference connector: Sage X3), which extracts their supply chain data. ADKMCP / FastMCPPrefectMLflowRustFSFastAPIDockerSage X3Multi-tenancyPython

Context

Flow Line, historically an ERP integrator now repositioning as an IT services company, has launched an AI platform that plugs into its clients’ ERP (reference connector: Sage X3, architecture designed to be ERP-agnostic) and extracts their supply chain data. On that foundation it delivers several decision services: sales forecasting, production scheduling and planning, anomaly detection and client prospecting, and replenishment optimisation up to raising purchase order proposals. The core relies on classical machine learning that is explainable, frugal and retrainable per client, and every capability is designed to be driven by AI agents. It is the group’s flagship product.

My role

Platform owner: I hold its architecture, and every technical and product decision goes through me. Within a four-person AI team, I industrialise the data science approaches validated upstream, turning them into reliable, secure, production-grade services.

Key deliverables

  • Architecture: a modular core per domain (forecasting, scheduling, anomalies, replenishment) on top of a shared ERP ingestion and normalisation layer, with a multi-tenant design and strict isolation of each client’s data
  • Industrialisation: orchestration with Prefect (ingestion, retraining, scheduled computation), model versioning and tracking with MLflow, artifacts and datasets on RustFS, testing, continuous integration, monitoring and failure recovery
  • Agentic layer (ADK + MCP servers built with FastMCP): each business capability exposed as a documented, agent-callable tool, with guardrails, human validation before any side-effecting action, and full traceability
  • Security and compliance: access control, secret management, isolation of client environments, auditable processing
  • Technical scoping of new use cases with the data science team, code review, and pre-sales support (demos, prospects’ technical and security requirements)
02 Production order scheduling · Agentic layer for APERAM Groupe Flow Line June 2026 Custom tool for planning and optimising production orders, commissioned by APERAM from Flow Line. ADKAI agentsChatbotOR-ToolsOperations researchLLMOpsPython

Context

APERAM commissioned Flow Line to build a bespoke planning and optimisation tool for production orders. The challenge: give planners a way to build, compare and adjust optimised production plans without going through a hard-to-use expert tool.

My role

The optimisation engine was built by the data science team. I joined the project to make it agentic: a tool driven in natural language, fully traceable and safe.

Key deliverables

  • Agentic layer (ADK) exposed through a chatbot, letting planners talk to the solver in natural language
  • Agent tooling: moving and rescheduling production orders, running the optimisation engine (OR-Tools), comparing scenarios, and summarising what each iteration changed
  • End-to-end traceability: logging of every agent action, change history, reversible decisions
  • Guardrails: business constraint checks and human validation before a plan is applied
03 Knowledge Hub · Agentic AI Platform Inetum, Lyon February 2025 – January 2026 Internal platform unifying access to documents, databases and company resources through a conversational AI agent. MCPAKSTerraformFlux CD / GitOpsAzure DevOpsFastAPIDjangoPythonLLMOps

Context

An internal platform for centralising and intelligently orchestrating knowledge, unifying access to documents, databases and enterprise resources through a conversational AI agent that answers in natural language (RAG, text-to-SQL, SQL-to-visualisation).

My role

Designed, developed and deployed the entire platform, except the initial API development, which I migrated from Flask to FastAPI.

Key deliverables

  • Built an MCP (Model Context Protocol) server that dynamically supplies contextual tools to the AI agent based on user queries
  • Deployed on Azure Kubernetes Service (AKS) with Terraform, with CD through Flux CD (GitOps)
  • CI pipelines in Azure DevOps (build, test, packaging, validation)
  • Integrated the AI modules (RAG, text-to-SQL, SQL-to-viz) into a scalable Kubernetes architecture, plus the user interface, conversational context and access rights
04 On-premise RAG Chatbot · Université Jean Moulin Lyon 3 Inetum, Lyon July 2025 – January 2026 Better access to information on Université Jean Moulin Lyon 3's Moodle platform. RAGVector databasesFastAPIKubernetesDockerPython

Context

Université Jean Moulin Lyon 3 wanted to improve access to information on its Moodle platform, where students and teaching staff regularly need help navigating courses, finding documents or obtaining administrative information.

My role

Designed and deployed an on-premise RAG chatbot on the university’s own infrastructure, guaranteeing the security and confidentiality of internal data.

Key deliverables

  • On-premise RAG chatbot answering in real time from the university’s internal document base
  • Moodle integration: automated lookup of teaching and administrative documents, guided navigation through courses
  • Structured the document base with the IT and teaching teams and iterated on answer relevance
  • Performance tracking and monitoring to guarantee the tool’s reliability and security
05 Knowledge transfer application · SNCF Inetum October – December 2025 Passing on the know-how of experienced SNCF staff to newcomers. Azure AI SpeechAzure OpenAIAzure AI SearchAzure Container AppsRAGCI/CDFinOpsPython

Context

SNCF wanted to pass on the know-how of its experienced staff to new joiners. A proof of concept had shown the full chain (interviews, transcription through Azure AI Speech, summarisation through Azure OpenAI, delivery through a RAG chatbot backed by Azure AI Search), but it was not usable as it stood: no tests, no reproducible deployment, no monitoring, and uncontrolled costs.

My role

Industrialised the solution: a complete refactor of the proof of concept into a deployable, maintainable, production-grade application.

Key deliverables

  • Reworked a monolithic prototype into a modular application: capture, transcription, summarisation, indexing and retrieval became isolated, testable, replaceable components
  • Production deployment on Azure Container Apps: containerisation, CI/CD, secret and managed-identity handling, separated environments, monitoring
  • Cost control: rationalised cognitive-service calls, caching and batch processing
  • Strict access partitioning for sensitive data, test coverage and documentation so SNCF’s own teams could take ownership
06 IRC · Crédit Agricole Technologies et Services Inetum, Lyon January – June 2025 Faster analysis and reporting of internal survey results, through automatically generated PowerPoint reports. AWS ECSAWS LambdaAWS CodePipelineCI/CDDockerGenAI

Context

Crédit Agricole Technologies et Services wanted to speed up the analysis and reporting of internal survey results through a platform that automatically produces PowerPoint reports with charts, combining RAG, automated visualisation and report generation.

My role

Infrastructure optimisation, deployment automation and technical delivery to the client.

Key deliverables

  • Reorganised the AWS ECS clusters and migrated selected functions to AWS Lambda, cutting cost and complexity
  • CI/CD pipelines with AWS CodePipeline: fast, reliable, reproducible releases with no manual steps
  • Handed over the codebase with documentation and supported the client in integrating it into their internal architecture (environments, security, interconnections)
07 Sovereign AI · On-premise AI Platform Atos, Montpellier August 2024 – January 2025 With Dell, a complete on-premise solution for putting AI models into production in regulated or sensitive sectors. KubernetesApache AirflowArgo CDMLflowDockerGitOpsPySparkPythonIaC

Context

Run in partnership with Dell, this project delivered a complete on-premise offering for putting AI models into production in regulated or sensitive sectors: optimised hardware infrastructure, a tailored MLOps stack, plus maintenance and governance services.

My role

Contributed to the design of the Sovereign AI platform, in particular its MLOps layer, from architecture choices through to technical implementation.

Key deliverables

  • Full MLOps infrastructure orchestrated with Kubernetes: data ingestion, training, deployment and monitoring of AI models
  • ML pipelines with Python and Apache Airflow, continuous model deployment with Argo CD, versioning and tracking with MLflow
  • Selected and integrated tooling suited to on-premise use: scalability, data security, maintainability
08 WWIN · Scottish Water (Wastewater Intelligent Network) Atos, Montpellier December 2023 – May 2024 Moving Scottish Water's wastewater network from reactive to proactive, predictive management, using 4,000 IoT sensors. Azure DatabricksPySparkMLflowAzure DevOpsMicrosoft AzurePythonIoT

Context

Scottish Water, Scotland’s main drinking water provider, wanted to move from reactive to proactive, predictive management of its wastewater network using real-time data from 4,000 IoT sensors, reducing pollution incidents and flooding and meeting SEPA’s regulatory requirements.

My role

Owned the MLOps side, within a multidisciplinary team (hydrologists, data scientists, data engineers, a data architect).

Key deliverables

  • End-to-end ML pipelines on Azure Databricks: ingestion, PySpark processing, model training and deployment, monitoring
  • Experiment tracking with MLflow
  • Continuous integration and delivery with Azure DevOps
09 AI 4 Code · Automated Vulnerability Remediation Atos, Montpellier August 2023 – August 2024 Helping DevOps teams without cybersecurity expertise automate the detection and remediation of code vulnerabilities. RAGReinforcement LearningKubernetesArgo CDRay ServeChromaDBLLMOpsDevSecOpsPython

Context

Help DevOps teams without cybersecurity expertise automate the detection and remediation of code vulnerabilities. The solution combines SAST/DAST tooling (KICS) with an on-premise LLM using RAG that automatically raises corrective pull requests.

My role

Designed and developed the platform’s technical infrastructure as a whole.

Key deliverables

  • On-premise infrastructure: Docker, Kubernetes, Airflow and Argo CD to orchestrate the analysis and fix-generation workflows
  • Ray Serve for distributed LLM calls, RAG with ChromaDB for contextual fixes
  • Reinforcement learning loop: prompts are refined automatically based on whether pull requests are accepted
  • Monitoring with Prometheus and Grafana, artifact storage with MinIO
  • Platform fully configurable through YAML (IaC), agnostic to projects, LLMs and Git repositories
10 FIDAMIA · Smart Categorisation of Citizen Reports Atos, Marseille April – June 2023 An AI solution to improve how the Aix-Marseille-Provence metropolis handles citizen reports. TraefikKongKubernetesNetwork securityNetwork architectureMLOps

Context

The Aix-Marseille-Provence metropolitan authority commissioned Atos to deliver an AI solution for handling citizen reports submitted through the “Ma Métropole Dans Ma Poche” mobile app. The aim: automate the categorisation of reported incidents (cleanliness, roads, signage) through image analysis, shortening response times for technical services.

My role

Set up the network and security infrastructure for industrialised AI model deployment on two virtual machines.

Key deliverables

  • Reverse proxies with Traefik and Kong: secure traffic management, request routing and controlled exposure of the AI services
  • Configured certificates, HTTPS redirection, and authentication and access restriction mechanisms
11 IoT Dataset Selection through Reinforcement Learning · Patents Atos, Montpellier March – June 2023Atos Inventor Trophy 2023 MLOps platform for anomaly detection on IoT data that dynamically selects its training datasets through reinforcement learning. Reinforcement LearningAnomaly DetectionApache AirflowDockerIoTPythonR&D / Patent

Context

Design of an MLOps platform for IoT data processing geared towards anomaly detection, whose main innovation is using reinforcement learning to dynamically select training datasets according to usage context and expected performance.

My role

Led the MLOps architecture design, developed the full data processing chain, and contributed to drafting the patent alongside Atos’ expert team.

Key deliverables

  • Full chain from IoT ingestion through to deployment of anomaly detection models
  • Reinforcement learning module driving dataset selection in production
  • Co-inventor on two patents: US2024412073A1 (United States) and EP4475044B1 (Europe, granted January 2026)
  • Winner of the 2023 Atos Inventor Trophy
12 MLSecOps Platform · ML Pipeline Integrity on the Blockchain Atos, Montpellier January – March 2023 Internal R&D mission at Atos: securing data processing and AI model deployment chains with the Ethereum blockchain. Ethereum BlockchainSmart ContractsSolidityMLOpsDockerDevSecOpsPython

Context

An internal Atos R&D assignment to build an MLSecOps platform securing the full chain of data processing and AI model deployment, by recording integrity hashes on the Ethereum blockchain through smart contracts.

My role

Developed and integrated the whole platform (smart contracts excepted).

Key deliverables

  • Secured MLOps chains from data ingestion through to model deployment
  • Integration with the Ethereum blockchain to verify the integrity of critical steps (datasets, models, artifacts)
  • Integrity proof mechanism through hashes published in smart contracts
  • Secured on-premise Docker infrastructure and automated verification workflows
13 Hospital Porter Logistics · Atout Majeur Concept Atout Majeur Concept, Quint-Fonsegrives June – August 2022 Improving how hospital porter workflows are managed, for a publisher of hospital software. CPLEX StudioMILPOperations researchMathematical modellingPython

Context

Atout Majeur Concept, a software publisher for hospitals, wanted to improve the management of patient portering flows. The objective: model porter assignment so as to minimise patient waiting times and optimise routes within the facility.

My role

Operations research engineer, responsible for designing and implementing the optimisation models.

Key deliverables

  • Mathematical modelling of the assignment problem with time, availability and priority constraints
  • Solved as mixed-integer linear programming (MILP) with CPLEX Studio
  • Proposed concrete improvement scenarios for the operational management of porters
14 Emergency Physicians' Rota Software · Castelnaudary Hospital Castelnaudary Hospital May 2021 A tool to track working hours and manage the rota of emergency physicians. VBAExcelSoftware engineering

Context

The emergency department at Castelnaudary Hospital needed a tool to track working time and manage the emergency physicians’ rota. The project involved the emergency department, medical affairs and the IT department.

My role

Sole developer, from writing the requirements through to delivery.

Key deliverables

  • Gathered requirements from the managers of each department involved
  • Built a rota management tool in Excel VBA, delivered in 2 weeks
  • Trained the head of department to carry on developing the tool
15 Dietary Supplement Search Interface · Institut Medicoach Institut Medicoach, Cépie May – June 2021 Making Institut Medicoach's database of dietary supplements and medicines available online. PHPJavaScriptHTML/CSSDatabase

Context

Institut Medicoach wanted to make its database of dietary supplements and medicines available online, with detailed information on each product: composition, therapeutic indications, interactions and contraindications.

My role

Sole web developer, from design to production.

Key deliverables

  • Built a search interface in PHP and JavaScript for querying the database
  • Product pages showing composition, properties, uses, compatibilities and incompatibilities
  • Integration and deployment on the institute’s infrastructure

Personal · in progress

Personal project

P · Personal project In progress

Neutreeko

PythonReinforcement LearningDQNJavaScriptGame dev
Play against the AI GitHub

  1. 01Context

    Neutreeko is an abstract two-player board game. This project started as a way to learn Python through practice, building something concrete rather than following tutorials. I now use it to learn about neural networks and reinforcement learning.

  2. 02Current state

    A first draft, started in my spare time: the game runs in Python (Pygame) with a first DQN agent, still weak, and a minimax search as the benchmark. You can play against them on this site.

  3. 03Next steps

    Keep learning by improving the agent, which still loses to the simplest minimax search. Ideas to try: training against minimax, board symmetries and network-guided search (AlphaZero-style).

Portfolio · skills · references

Going further

Download the full portfolio (PDF) See my skills References