Senior AI Engineer (f/m/d)

Worldwide | Oct. 14, 2026

Report as Closed

Company: Decathlontechnology

Country: Worldwide

Type: Onsite

Employment: Full-time

Description:

About Decathlon

Decathlon aspires to become the best digital sports platform and open ecosystem in the world. We want to allow customers to live the Decathlon experience through numerous local experiences centered on sport by connecting numerous third-party players and services, in a secure and efficient manner.

Our digital teams based in Lille and Paris (and more...) bringing together more than 5,000 employees, are united to design and develop digital products with the objective of always offering the best value to our users. Present in more than 70 countries, Decathlon is committed to innovation, sustainability and customer satisfaction.

Job Description

Our PRISM (Supply Chain) team is looking for an AI Engineer based in Paris. As an AI Engineer dedicated to the deployment of agents, you will be at the heart of a tight technical team. You will play a critical role in the industrialization, deployment and monitoring of our agentic capabilities. You will work closely with the digital teams (Data, Product, Engineering) to architect the deployment infrastructure, design the intelligence routing and build a secure infrastructure allowing our agents to natively interact with our business data and legacy systems

Responsibilities

• Design and deploy the solid foundations that will allow our AI agents to be hosted, run and interact seamlessly with our systems when released into production.
• Design robust pipelines enabling multi-stage asynchronous agentic execution (e.g. transactional ingestion and write flows), by implementing distributed resilience patterns.
• Integrate agentic orchestration SDKs (notably Google Vertex AI Agent SDK / ADK), bypassing the “black box” limitations of managed frameworks.
• Efficiently orchestrate the agents put into production while guaranteeing good management of information processing, routing to the most suitable models and guaranteeing optimal cost management and use of tokens. Guarantee and ensure the quality and speed of execution of the tasks to be carried out.
• Strictly frame the scope of action of each agent. You guarantee that they only access the data and actions for which they are formally authorized, in compliance with our confidentiality rules. By guaranteeing data security.
• Build advanced performance measurement and tracking pipelines to trace the agent's thoughts and decisions from end to end in order to debug the logic in production.
• Work with the team to define relevant and consistent data evaluation metrics in relation to the defined functional specificities and metrics.

Know-How

• Design of robust backends (Python), operational control of containerization (Docker, Kubernetes) and pipelines (CI/CD, automated tests, observability, log management) to ensure robust production releases.
• Production-focused Python expertise, mastery of deployment platforms (Vertex AI Agent Builder, Gemini Enterprise Agent Platform) and client/server integration protocols such as Model Context Protocol (MCP).
• Experience in optimizing context windows for massive boundary models. Routing of requests to models adapted to the envisaged solutions
• Ability to build testing frameworks for LLMs (LLM-as-a-Judge, Golden Datasets), mastery of deterministic metrics and strict validation of output formats (JSON schema enforcement).
• Hands-on experience with Agentic RAG, Semantic Caching to reduce latency and API costs, or the use of prompt optimization frameworks (e.g. DSPy).
• Experience applied to supply chain, retail, or model deployment via Databricks / MLFlow.

Knowledge

• Excellent communication and collaboration skills.
• Ability to work effectively in a dynamic and fast-paced environment.
• Strong problem-solving skills and attention to detail.&l

  Apply here:

  Web: Apply here

  ☆ Save job

  Emails: