Ph3Senior AI Engineer – RAG / Azure AI Platform (Consultancy Assignment) /h3 pWe are looking for a Senior AI Engineer to join the Digital Innovation / AI Center of Excellence team during the Build and early Run phases of the service. You will work closely with the AI Platform Architect and Solution Architect to transform the high-level design into a production‑ready, scalable, and maintainable system. /p h3Responsibilities /h3 ul liDesign and implementation of a full RAG pipeline (retrieval, reranking, LLM orchestration, citation handling) /li liDevelopment of ingestion pipelines (CMS document sources such as SharePoint), including chunking and embedding strategies /li liImplementation of security trimming and access control propagation (ACL-based filtering) /li liDesign of prompt templates, guardrails, and safety mechanisms /li liSetup of evaluation frameworks to measure search and LLM performance /li liInfrastructure‑as‑Code using Terraform for Azure resources /li liDeployment automation using Azure DevOps pipelines and Helm charts on AKS /li liOperational tuning and optimization during early production run /li /ul h3Tech Environment /h3 ul liAzure OpenAI, Azure API Management, Azure AI Content Safety /li liKubernetes (AKS) /li liVector databases / search index (open‑source / self‑hosted) /li liPython‑based AI/ML pipelines /li liTerraform, Helm, Azure DevOps /li liRAG frameworks and LLM orchestration tooling /li /ul h3Engagement Model /h3 ul liAssignment via consultancy (freelancer or contractor via our organization) /li liHybrid enterprise environment with strong engineering ownership /li liLong‑term engagement (initial period with possible extension up to ~3+ years equivalent scope) /li /ul h3Screening Questions /h3 ul liHave you personally built or led the implementation of a Retrieval‑Augmented Generation (RAG) system that went to production? /li liIf yes: please describe the RAG system briefly (business domain, approximate document corpus size, retrieval stack used including embeddings, vector store, reranking if any, and retrieval quality metrics). (max 300 words) /li liHave you personally authored Kubernetes manifests or Helm charts and Terraform code for Azure as part of deploying an AI or ML workload to production? /li liIf yes: please provide one concrete example where you were personally responsible for both Kubernetes (manifests or Helm charts) and Terraform. (max 200 words) /li liHave you designed and implemented an evaluation framework (metrics, test sets, automation) for a RAG or LLM application you worked on? /li liIf yes: please describe the evaluation methodology, including metrics used, test set creation, and how evaluation was integrated into the deployment or iteration cycle. (max 200 words) /li liThis role requires on‑site presence in Brussels 2 to 3 days per week. Are you willing and able to commit to this schedule? /li /ul /p #J-18808-Ljbffr