AI Engineer – Production Agent Orchestration (Remote 2d/wk)

Decathlon Digital EN; Paris; Hybride; EUR 90 000 - 130 000; Plein temps

Avantages offerts par ce poste

2 days remote work per week

Office options: Lille, Paris, or amSrd

Equipment provided (Mac/Windows/Chrome

Local project team within a global net

Technical training and certifications

Profit-sharing in company shares +Bonu

Résumé du poste

Decathlon Digital EN is seeking an AI Engineer in Paris to drive the industrialization, deployment, and monitoring of agent capabilities within the PRISM Supply Chain team. You will architect deployment infrastructure, design intelligent routing, and secure data interactions with corporate data and legacy systems.

You will build robust production pipelines, integrate agent SDKs, and optimize model routing and costs while maintaining strict data security and traceability across end-to-end agent

Qualifications

• Senior profile with solid experience in Machine Learning Engineering focused on production infrastructure release.

Responsabilités

• Design and deploy foundations for hosting AI agents in production.
• Build robust asynchronous multi-step pipelines for agent execution.
• Integrate agent orchestration SDKs (Google Vertex AI Agent SDK/ADK).
• Orchestrate agents in production optimizing cost and token usage.
• Ensure agents access only authorized data and actions per confidentiality rules.
• Develop end-to-end traces for agent reflections and decisions for debugging.
• Define data evaluation metrics aligned with functional specs.

Connaissances

Python

Docker

Kubernetes

CI/CD

LLMs

Vertex AI

Databricks

GCP

Model Deployment

Outils

Vertex AI Agent Builder

Gemini Enterprise Agent Platform

Protobuf

gRPC

Docker

Kubernetes

Description du poste

Decathlon aspires to become the world's best sports digital platform and open ecosystem. We want to enable customers to experience Decathlon through numerous local sports-centric experiences by connecting many third-party actors and services in a secure and high-performance manner.

Our digital teams in Lille and Paris (and more...) grouping over 5000 employees, are united to design and develop digital products with the goal of always offering the best value to our users. Present in over 70 countries, Decathlon is committed to innovation, sustainability, and customer satisfaction.

Job Description

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

Responsibilities

• Design and deploy solid foundations that will allow our AI agents to be hosted, run, and interact smoothly with our systems during production release.
• Design robust pipelines enabling multi-step asynchronous agentic execution (e.g., transactional ingestion and writing flows), by implementing distributed resilience patterns.
• Integrate agentic orchestration SDKs (notably Google Vertex AI Agent SDK / ADK), bypassing "black box" limitations of managed frameworks.
• Efficiently orchestrate agents in production while ensuring proper information processing, routing to the most suitable models, and guaranteeing optimal cost and token usage management. Also ensure quality and speed of task execution.
• Strictly define the scope of action for each agent. You guarantee they only access data and actions for which they are formally authorized, respecting our confidentiality rules, while ensuring data security.
• Build advanced performance measurement and tracking pipelines to trace agent reflections and decisions from end to end in order to debug logic in production.
• Work with the team to define relevant and consistent data evaluation metrics relative to the defined functional specificities and metrics.

Hard Skills

• Robust backend design (Python), operational mastery of containerization (Docker, Kubernetes) and pipelines (CI/CD, automated testing, 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 like the Model Context Protocol (MCP).
• Experience optimizing context windows for massive frontier models. Request routing to models suitable for the selected solutions.
• Ability to build test frameworks for LLMs (LLM-as-a-Judge, Golden Datasets), mastery of deterministic metrics and strict validation of output formats (JSON schema enforcement).
• Practical experience with Agentic RAG, Semantic Caching to reduce latency and API costs, or using prompt optimization frameworks (e.g., DSPy)
• Applied experience in supply chain, retail technology, or model deployment via Databricks / MLFlow

Soft Skills

• Excellent communication and collaboration skills.
• Ability to work effectively in a dynamic and fast-paced environment.
• Strong problem-solving skills and attention to detail.
• Adaptability and willingness to learn new technologies and methodologies and share them.
• Ability to translate complex technical concepts into understandable terms for non-technical stakeholders.
• Ability to understand user challenges and associated needs.

Qualifications

• Senior Profile: You have solid experience (Machine Learning Engineering) with a strong focus on production infrastructure release.
• Ability to leverage managed solutions (Vertex AI) while knowing how to "dive into code" to debug distributed architectures, develop custom connectors, and bypass framework limitations.
• Demonstrated ability to evolve in shifting technical environments.
• Operational skills on GCP and understanding of containerized environments (Docker, Kubernetes) to autonomously deploy the Agentic layer.

Technical Environment

• AI & Integration Protocols: Model Context Protocol (MCP), LLMs (Gemini), LLM routing & memory management.
• Security & Access: Google Cloud Model Armor.
• Execution Engine: Databricks, AWS EKS, Sagemaker
• Payload: Python, Spark, Scikit-Learn, Tensorflow / Pytorch, Pyspark
• CICD: Github Actions
• Serving: Docker, Protobuf, gRPC
• Orchestration: Airflow
• Documentation / code: Git, Confluence

WHAT WE OFFER YOU

• 2 days of remote work per week;
• Possibility to work in one of the Decathlon Digital offices in Lille, Paris, or Amsterdam;
• Equipment provided according to your missions and our societal commitments (Mac, Windows, or Chromebooks);
• A local project team within a global network (possibility of international career);
• Skills development and support (diversity of projects, technical certifications from the first year, internal and external training, etc.);
• Remuneration package (employee profit-sharing in company shares, monthly/quarterly bonuses).

Joining Decathlon means being part of a dynamic team passionate about sport, innovation, and having a positive impact on our customers' lives. If you are excited about leveraging data science to optimize supply chain processes and drive business growth, we invite you to apply and be part of our adventure!

What if technology allowed us to push the boundaries and take sports experiences to new levels? That's exactly our goal at Decathlon Digital! We are a team of 5,000+ experts in software engineering, product management, data, cloud, and cybersecurity, distributed across Paris, Lille, and Amsterdam. Together, we are creating the largest digital sports platform, leveraging tech innovation from design to value chain optimization, connected experiences and product second life.

Changing the game for good. We are in this for the love of sports. And like everything we love, we want it to last. That’s why we are embarking on a journey to create a more sustainable tech model, reducing our direct environmental impact while maintaining a safe, diverse, and inclusive space for all our people to learn and thrive together. Team up with us to design the digital future of sports.

Create a Job Alert

Interested in building your career at Decathlon Digital EN? Get future opportunities sent straight to your email.

Accepted file types: pdf, doc, docx, txt, rtf

Enter manually

Accepted file types: pdf, doc, docx, txt, rtf

LinkedIn Profile

Website

RGPD / GDPR : * Select...

GDPR : When you apply to a job on this site, the personal data contained in your application will be collected by Decathlon SE, (“Controller”), which is located at 4 Boulevard de Mons 59650 Villeneuve d'Ascq. Your personal data will be processed for the purposes of managing Controller’s recruitment related activities. Your personal data will be retained by Controller as long as Controller determines it is necessary to evaluate your application for employment but for no longer than 2 years.

• You have the right to request access to your personal data, to request that your personal data be rectified or erased, and to request that processing of your personal data be restricted.
• You also have the right to data portability. You can request these rights by clicking here .