AI Engineer (f/m/d)
Paris, Paris, France • Full-time
Posted 1mo ago
Job Location
Paris, Paris, France
Tech Stack
Remote Work Policy
On-site
Employment Type
Full-time
Categories
AI Agent Engineer
About the job
Our PRISM (Supply Chain) team is seeking an AI Engineer to be based in Paris. As an AI Engineer dedicated to the deployment of agents, you will be at the heart of a close-knit technical team. You will play a critical role in industrializing, deploying, and monitoring our agentic capabilities. You will work closely with digital teams (Data, Product, Engineering) to architect the deployment infrastructure, design intelligence routing, and build a secure infrastructure enabling our agents to interact natively with our enterprise data and legacy systems.
Responsibilities
- Design and deploy robust foundations for hosting, executing, and enabling AI agents to interact seamlessly with systems in production.
- Design robust pipelines for multi-step asynchronous agentic execution, implementing distributed resilience patterns.
- Integrate agentic orchestration SDKs (e.g., Google Vertex AI Agent SDK/ADK), overcoming limitations of managed frameworks.
- Efficiently orchestrate production agents, ensuring proper information processing, routing to appropriate models, and optimal cost/token management.
- Strictly define the scope of action for each agent, ensuring they only access authorized data and actions according to privacy rules and data security.
- Build advanced performance measurement and tracking pipelines to trace agent reasoning and decisions end-to-end for production debugging.
- Collaborate with the team to define relevant data evaluation metrics aligned with functional specifications.
Requirements
- Design of robust backends (Python), operational mastery of containerization (Docker, Kubernetes) and pipelines (CI/CD, automated tests, observability, log management).
- Production-focused Python expertise, mastery of deployment platforms (Vertex AI Agent Builder, Gemini Enterprise Agent Platform) and integration protocols (MCP).
- Experience optimizing context windows for large frontier models and routing requests to appropriate models.
- Ability to build test frameworks for LLMs (LLM-as-a-Judge, Golden Datasets), mastery of deterministic metrics, and strict validation of output formats.
- Hands-on experience with Agentic RAG, Semantic Caching for latency/cost reduction, or prompt optimization frameworks (e.g., DSPy).
- Applied experience in supply chain, retail, or model deployment via Databricks/MLFlow.
- Solid experience in Machine Learning Engineering with a strong focus on production infrastructure.
- Ability to leverage managed solutions (Vertex AI) while also delving into distributed architectures, developing custom connectors, and overcoming framework limitations.
- Demonstrated ability to thrive in evolving technical environments.
- Operational proficiency on GCP and understanding of containerized environments (Docker, Kubernetes) for autonomous agentic layer deployment.
