Senior AI Engineer — RAG Applications JP053929

Job Opportunity: Senior Artificial Intelligence (AI) Engineer

Location: Bruxelles (Cantersteen) Duration: ASAP 31/12/2026 (Initial 9-month contract with potential extension up to 880 working days) Work Arrangement: Full-time

Role Overview

We are seeking a highly skilled Senior AI Engineer to join a leading Digital Innovation / AI Center of Excellence (CoE) team. This role is pivotal for the Build and early Run phases of a flagship RAG-based (Retrieval-Augmented Generation) knowledge search service.

Serving approximately 10000 employees this bilingual (French/Dutch) AI solution is the first production service on a newly established enterprise AI Platform. You will work in close collaboration with the internal AI Platform Architect and Solution Architect to transform high-level designs into a robust evaluated and maintainable production service.

Key Responsibilities

1. RAG Pipeline Development

• End-to-End Implementation: Build and optimize the full RAG lifecycle including sophisticated retrieval strategies reranking logic LLM orchestration and precise citation handling.
• Ingestion & Processing: Develop high-performance ingestion pipelines featuring connectors for Jahia CMS and SharePoint.
• Data Engineering: Implement intelligent document chunking embedding generation and management of vector stores.

2. Infrastructure & Deployment

• Hybrid Cloud Management: Operate within a hybrid environment utilizing managed Azure services (OpenAI API Management Content Safety) and self-hosted open-source components on Azure Kubernetes Service (AKS).
• Infrastructure as Code (IaC): Own and manage application-scoped Azure resources using Terraform and Azure DevOps CI/CD pipelines.
• Containerization: Develop and maintain Helm charts for service deployment on AKS.

3. Quality Security & Governance

• Security & Compliance: Implement rigorous security trimming and Access Control List (ACL) propagation to ensure data privacy.
• Prompt Engineering: Design and refine prompt templates and integrated guardrails to ensure output accuracy and safety.
• Evaluation: Build and maintain an evaluation harness to systematically measure and improve model performance (accuracy relevancy and groundedness).

Technical Profile & Requirements

Core Engineering Skills:

• Python: Advanced proficiency; ability to write clean scalable and production-ready code.
• Terraform: Advanced expertise in Infrastructure-as-Code for Azure environments.
• Azure Kubernetes Service (AKS): Advanced experience in deploying and managing containerized applications.
• Azure DevOps: Advanced skills in managing pipelines and automated releases.

AI & LLM Expertise:

• RAG (Retrieval-Augmented Generation): Intermediate to Advanced understanding of RAG architectures and optimization.
• LLMs: Practical experience working with Large Language Models (specifically Azure OpenAI Service).
• Vector Databases: Solid understanding of vector storage indexing and retrieval mechanics.

Language Requirements:

• French or Dutch: Native or bilingual proficiency (the service is bilingual).
• English: Full professional proficiency for technical collaboration and documentation.

What to Expect

This is a mission-critical project where you will transition from initial development into the early operational tuning phase. You will be a key contributor to an AI CoE that is setting the standard for future AI services within a large-scale public organization.