AI Engineer - STIB-MIVB

Adjugo; Brussel Hoofdstad; Hybrid; EUR 70,000 - 110,000; Full time

Benefits offered by this job

Hybrid work model

On-site in Brussels 2-3 days/week

Job summary

STIB-MIVB is seeking a Medior AI Engineer to own production operations for AI services inside the AI Center of Excellence. You’ll monitor availability, latency and errors, drive cost efficiency, and collaborate with the internal AI Platform Architect and other engineers.

You’ll maintain ingestion pipelines, ensure data protection, and manage Terraform/Helm/DevOps artefacts across DEV, TST, ACC and PROD environments.

Qualifications

• RAG (Retrieval-Augmented Generation) intermediate proficiency.
• English: full professional proficiency.
• Dutch or French: native or bilingual proficiency (one of the two languages).

Responsibilities

• Operate the AI services in production: monitor availability, latency and errors, handle incidents and service requests, analyse root causes, then fix or elevate.
• Maintain evaluation sets and track answer quality, non-answer rate and user feedback.
• Operate the ingestion pipelines: incremental refresh, failed documents, index health, and onboarding of new content sources.
• Operate agent integrations: monitor tool and integration calls to business systems, handle failures and timeouts, and review logs.
• Maintain Terraform, Helm and Azure DevOps artefacts, and keep DEV, TST, ACC and PROD environments consistent.
• Apply data protection rules: trace retention, erasure and access restrictions.

Skills

RAG proficiency

English proficiency

Dutch/French bilingual

Tools

Azure DevOps

AKS (Azure Kubernetes Service)

Azure OpenAI Service

LangChain

LLM / Large Language Models

Python

Terraform

Vector databases

Job description

Dates: 2027-01-04 - 2028-01-03

Arrangements: Full time; hybrid; on-site in Brussels 2 to 3 days per week.

STIB-MIVB is building employee- and customer-facing AI services across the organization. Services range from retrieval-based assistants to AI agents that call tools and business systems on users' behalf. They run on the STIB AI Platform. The first services go live from December 2026, with more following in 2027.

The Medior AI Engineer joins the AI Center of Excellence's Digital Innovation & AI delivery team and owns production operations. Each service is handed over by the Senior AI Engineers who built it. The engineer keeps services reliable, measured, secure and cost-efficient. Collaboration includes the internal AI Platform Architect, two Senior AI Engineers responsible for Build, business and content owners, and IT operations teams.

The platform combines managed Azure services with self-hosted open-source components on AKS. Microsoft Foundry uses the OpenAI model family for LLMs and embeddings, alongside Azure AI Search, Azure API Management and Azure AI Content Safety. Python and LangChain support agent orchestration and an ingestion pipeline, with MLflow on Databricks for evaluation and OpenTelemetry tracing. The team owns application-scoped Azure Infrastructure-as-Code through Terraform and Azure DevOps pipelines; small enhancements belong to Run, while structural changes and new features stay with Build.

Top Reasons to Apply

Production AI ownership

Agents and RAG

Public transport impact

Cross-functional AI collaboration

Responsibilities

operate the AI services in production: monitor availability, latency and errors, handle incidents and service requests, analyse root causes, then fix or elevate ;

keep answer quality under control: run and maintain evaluation sets (golden sets) with business content owners, track answer quality, non-answer rate and user feedback, and detect and investigate quality regressions ;

operate the ingestion pipelines: incremental refresh, failed documents, index health, and onboarding of new content sources or business domains within existing connectors ;

operate agent integrations: monitor tool and integration calls to business systems, handle failures and timeouts, and review action logs and exceptions for agents that act on users' behalf ;

manage change safely: model version upgrades and retirements, prompt and configuration changes, dependency and security updates, each validated against the evaluation sets before release ;

follow run cost: token consumption and cost per service, alerting on drift and proposing optimisations ;

maintain the Terraform, Helm and Azure DevOps artefacts, and keep the DEV, TST, ACC and PROD environments consistent ;

apply data protection rules: trace retention, erasure and access restrictions, as defined in each service's data protection impact assessment ;

Must Have

RAG (Retrieval-Augmented Generation) intermediate proficiency

Detailed Responsibilities and Skills

Additional Responsibilities

• maintain runbooks and documentation, and report service health to service owners and the AI CoE on a regular basis ;
• deliver small enhancements and fixes; structural changes and new features stay with the Build team.
• Medior Artificial Intelligence (AI) Engineer; most recent experience: this year (2026).
• Dutch or French: native or bilingual proficiency (one of the two languages).
• English: full professional proficiency.
• On-site presence in Brussels 2 to 3 days per week.

Technical skills and tools

• Azure DevOps: intermediate level; most recent experience: this year (2026).
• Azure Kubernetes Service - AKS: intermediate level; most recent experience: this year (2026).
• Azure OpenAI Service: intermediate level; most recent experience: this year (2026).
• LangChain: intermediate level; most recent experience: any time.
• LLM / Large Language Models: intermediate level; most recent experience: this year (2026).
• Python: intermediate level; most recent experience: this year (2026).
• RAG (Retrieval-Augmented Generation): intermediate level; most recent experience: this year (2026).
• Terraform: intermediate level; most recent experience: this year (2026).
• Vector databases: intermediate level; most recent experience: this year (2026).

Selection questions — status not stated as mandatory

• Question 1 screens for at least 6 months personally operating or supporting a production LLM application (RAG, agent or document processing).
• Question 2 asks for personal investigation of an LLM or agent quality issue or incident using traces or logs.
• Question 3 asks for running or maintaining LLM evaluations, including test sets after model or prompt changes.
• Question 4 asks for personal deployment of Kubernetes manifests or Helm charts and Terraform code through Azure CI/CD pipelines.