Skip to main content
ITproposal

Senior AI Engineer

3w

ITproposal

Brussels, BE · Contract · €85,000 – €125,000

About this role

We are seeking a highly skilled Senior AI Engineer to join a leading Digital Innovation / AI Center of Excellence team. This role is pivotal for the Build and early Run phases of a flagship RAG-based knowledge search service. It serves approximately 10,000 employees as a bilingual French/Dutch AI solution on a new enterprise AI Platform.

You will collaborate closely with the internal AI Platform Architect and Solution Architect to transform high-level designs into a robust, evaluated, and maintainable production service. Develop end-to-end RAG pipelines including sophisticated retrieval strategies, reranking logic, LLM orchestration, and citation handling. Handle ingestion from Jahia CMS and SharePoint with intelligent document chunking and embedding generation.

Operate in a hybrid cloud environment using managed Azure services like OpenAI, API Management, and Content Safety alongside self-hosted components on Azure Kubernetes Service. Manage infrastructure as code with Terraform and Azure DevOps CI/CD pipelines while developing Helm charts for deployments. Ensure quality through security trimming, ACL propagation, prompt engineering, and evaluation harnesses.

Join the first production service on the enterprise AI Platform in Brussels. Start ASAP on an initial 9-month full-time contract with potential extension up to 880 working days. Contribute to a high-impact knowledge search service for thousands of users.

Requirements

  • Advanced proficiency in Python; ability to write clean, scalable, and production-ready code
  • Advanced expertise in Terraform for Infrastructure-as-Code in Azure environments
  • Advanced experience in Azure Kubernetes Service (AKS) deploying and managing containerized applications
  • Advanced skills in Azure DevOps managing pipelines and automated releases
  • Intermediate to Advanced understanding of RAG architectures and optimization
  • Practical experience working with Large Language Models, specifically Azure OpenAI Service
  • Solid understanding of vector databases, storage, indexing

Responsibilities

  • Build and optimize the full RAG lifecycle, including sophisticated retrieval strategies, reranking logic, LLM orchestration, and precise citation handling
  • Develop high-performance ingestion pipelines featuring connectors for Jahia CMS and SharePoint
  • Implement intelligent document chunking, embedding generation, and management of vector stores
  • Operate within a hybrid environment utilizing managed Azure services and self-hosted components on Azure Kubernetes Service (AKS)
  • Own and manage application-scoped Azure resources using Terraform and Azure DevOps CI/CD pipelines
  • Develop and maintain Helm charts for service deployment on AKS
  • Implement rigorous security trimming and Access Control List (ACL) propagation to ensure data privacy
  • Design and refine prompt templates and integrated guardrails; build evaluation harness to measure model performance

Benefits

  • Initial 9-month contract with potential extension up to 880 working days