AI Engineer (AI & GenAI) - Finance Domain

As part of the opening of a permanent position, we are recruiting an AI Engineer, based optionally in Lille or Paris.

🚀 CONTEXT & STRATEGIC CHALLENGES

Within Decathlon Digital, the Finance Data team is launching a major initiative: transforming finance professions through the integration of Generative and Agentic AI.

Faced with the fragmentation of analyses performed by the FP&A function, our ambition is to build more standardized solutions with the support of AI. This involves implementing centralized intelligence layers, agnostic of tools, capable of interacting with our entire infrastructure (Workday, Data Lake, EPM, ...) to evolve our interfaces from a consultation logic to an action logic.

In this context, we are developing AI-generated financial performance debriefs for all company activities. It helps our employees and managers to instantly access reliable information on which they can make decisions.

Already successfully deployed in France, Spain, Italy, and Belgium, this project is the first of a series to come.

To lead this project, we are not just looking for a developer; we need a "Builder": a person capable of translating a business need into a technical solution, implementing it, qualifying it, deploying it, and maintaining it over time.

 🎯 YOUR MISSION

We are looking for an experienced AI Engineer to actively participate in the industrialization and development of our AI solutions for management controllers. Your objective is clear: to transform business needs into reliable, measurable, and robust AI functionalities.

To take on this challenge, you will work within a dedicated team, in direct collaboration with other AI Engineers and a Product Manager. This close-knit organization will allow you to ensure perfect synergy between product challenges, the roadmap, and technical implementation.

🛠 YOUR RESPONSIBILITIES 

1. Agentic Development & Functionalities

• Participate in extending our agents' capabilities to writing actions by implementing tool-calling protocols (MCP - Model Context Protocol) and inter-agent communications (A2A).
• Contribute to optimizing costs, latency, and overall system efficiency in conjunction with the Platform and Infrastructure teams.

1. Quality, Evaluation & Observability (LLMOps)

• Develop and maintain the quality layer of our pipelines (Databricks / Vertex AI Search / Discovery Engine).
• Ensure the grounding of responses and verification of citations to guarantee traceability to a source of truth.
• Implement robust observability pipelines for online and offline evaluation (OpenTelemetry, MLflow, Langfuse).
• Code automatic evaluators to iterate confidently and prevent regressions before each production deployment.
• Integrate guardrails to protect the system and users from hallucinations and errors.

1. Security, Isolation & International Deployment

• Isolation & Multi-tenancy: Implement metadata filtering strategies in vector databases and isolation (of indexes and/or models) to ensure perfect data impermeability between Decathlon's various tax companies, legal entities, and geographies.
• Multilingual Support: Contribute to the internationalization architecture of our solutions by adapting pipelines, embedding, and inference to maintain a high level of performance and relevance across a wide diversity of languages.

1. Product & Business Impact

• Assist in analyzing user intentions to measure product impact.
• Translate business challenges into model behaviors and success metrics, with the support of the Product Manager.

🧠 PROFILE SOUGHT

We are looking for a profile with at least a first experience.

• Experience: Experienced profile with several years of professional corporate experience (excluding internships and apprenticeships) in AI Engineering, ML Engineering, or AI-oriented Software Engineering. You also have at least one concrete and successful experience deploying a GenAI or agentic system into production.
• Technical Stack: Solid mastery of Python, the GCP / Vertex AI + Databricks ecosystem, and orchestration frameworks (LangChain, LlamaIndex, or Google ADK).
• LLM & Agentic Expertise: Solid mastery of RAG architectures (vector search, Vertex AI Vector Search, advanced metadata management), but above all agentic technical concepts: function/tool-calling, reasoning loops (ReAct, etc.), multi-agent workflow orchestration, structured output, and context/memory management.
• Quality & Evaluation: Ability to diagnose an incorrect response (model, retrieval, or data issue) and aptitude for application observability (SQL / MLflow).
• Languages: Fluent French mandatory & fluent professional English (international environment).

The Plus Points: 

• In-depth technical knowledge of A2A (Agent-to-Agent) and MCP protocols.
• Technical understanding of security issues (RBAC, ACLs, GDPR) applied to LLMs.
• Knowledge of microservices architectures and API design.

🎁 WHAT WE OFFER

• The opportunity to develop a cutting-edge agentic AI product with a direct impact on employees' daily lives.
• A premium technological environment (Google Cloud / Vertex AI / Databricks Stack).
• A flexible remote work policy (2 days per week remote, the rest in our offices).
• A delivery culture focused on autonomy, collective intelligence, and skill development (mentorship by a Lead, certifications, training).
• Attractive benefits (monthly/quarterly bonuses, employee share ownership).