Senior AI Engineer — RAG Applications (Azure / Kubernetes) (JP056186)

TiTANS België; Brussel Hoofdstad; Hybrid; EUR 90,000 - 140,000; Full time

Job summary

STIB-MIVB is looking for a Senior AI Engineer to join the Digital Innovation / AI CoE. You will deliver end-to-end RAG pipelines, ingestion and embedding workflows, and robust guardrails in a hybrid Brussels-based environment.

Work involves Terraform/Helm-based deployments on Azure, observability, and cost control, with collaboration across project teams and platforms. On-site presence in Brussels 2–3 days per week is required.

Qualifications

• Experience building Retrieval-Augmented Generation (RAG) systems in production.
• Proficiency with Kubernetes manifests or Helm charts and Terraform for cloud deployments.
• Ability to design evaluation frameworks for LLM-based applications and track metrics.

Responsibilities

• Deliver end-to-end RAG pipeline including retrieval strategy and answer generation.
• Build and maintain ingestion and embedding pipelines with source connectors.
• Implement security trimming, ACL propagation and access control in the retrieval layer.
• Develop agent orchestration, prompt templates, and guardrails.
• Set up evaluation, tracing, and cost-control instrumentation for the service.
• Create Terraform, Helm and Azure DevOps artefacts to deploy and operate the service.
• Support hypercare and handover of the service to Run phase.

Skills

LangChain

Python

RAG

Terraform

Tools

Terraform

Helm

Azure DevOps

Job description

STIB-MIVB (Brussels public transport operator) is building several employee- and customer-facing AI services, serving our customers and employees across the organization. The AI services are build and ran on our STIB AI Platform.

Your role

We are recruiting a Senior AI Engineer to join the Digital Innovation / AI CoE team for the Build and hypercare phases of some our most complex AI services. You will work alongside STIB's internal AI Platform Architect, the other Senior AI Engineer (already on board), and the project teams (project manager, business analyst, solution architect), turning our AI projects into running, evaluated and maintainable services.

The AI Platform runs on a hybrid operating model: managed Azure services (Azure AI Foundry with the OpenAI model family for LLM and embeddings, Azure AI Search, Azure API Management, Azure AI Content Safety) combined with self-hosted open-source components on AKS (agent orchestration in Python with LangChain, ingestion pipeline), with MLflow on Databricks for evaluation and tracing. The Digital Innovation / AI CoE team owns Infrastructure-as-Code for all application-scoped Azure resources, using Terraform and Azure DevOps pipelines.

What you will deliver

Activities will vary from project to project. Typically you will deliver:

• the RAG pipeline end-to-end, from retrieval strategy to answer generation ;
• the ingestion pipeline: connectors to source platforms, chunking, embedding, incremental refresh ;
• security trimming and ACL propagation ;
• agent orchestration, prompt templates and guardrails ;
• the evaluation and tracing setup: offline evaluation sets, retrieval and answer-quality metrics, end-to-end tracing of requests and agent steps ;
• the Terraform, Helm and Azure DevOps artefacts needed to deploy and operate the service ;
• Observability and cost control: instrumentation for latency, token consumption and run cost, plus quality regression detection after model or prompt changes ;
• Hypercare and early production: incident analysis, tuning, runbooks and documentation, and handover of the service to the engineer who will own the Run phase.

Roles

Senior Artificial Intelligence (AI) Engineer

Skills

• LangChain
• Python
• RAG (Retrieval-Augmented Generation)
• Terraform

Languages

Dutch or French (native or bilingual proficiency), English (full professional proficiency)

Questions

• Have you personally built or led the implementation of a Retrieval-Augmented Generation (RAG) system that went to production? (if answer to Q1 is "Yes") Please describe the RAG system briefly: business domain, approximate document corpus size, retrieval stack used (embeddings, vector store, reranking if any), and the retrieval quality metrics you measured. Maximum 300 words.
• Have you personally authored Kubernetes manifests or Helm charts and Terraform code for Azure, as part of deploying an AI or ML workload to production? (if answer to Q2 is "Yes") Please give one concrete example where you were personally responsible for both the Kubernetes (manifests or Helm charts) and the Terraform code. Maximum 200 words.
• Have you designed and implemented an evaluation framework (metrics, test sets, automation) for a RAG or LLM application you worked on? (if answer to Q3 is "Yes") Please describe the evaluation methodology: which metrics you used, how you curated or generated test sets, and how evaluation was integrated into your deployment or iteration cycle. Maximum 200 words.
• Have you personally implemented document-level access control in a RAG system, so that users only see content they are authorised to access in the source platform? (if answer to Q4 is "Yes") Briefly describe how permissions were propagated from the source system to the retrieval layer, and how you tested it. Maximum 200 words.
• This role requires on-site presence in Brussels 2 to 3 days per week. Are you willing and able to commit to this schedule?