Medior AI Engineer – LLMOps & Run for AI Agents and RAG

HumanInTech; Brussel Hoofdstad; Hybrid; EUR 70,000 - 100,000; Full time

Job summary

HumanInTech in Brussels is looking for an AI Run engineer to own the Run phase of production AI services built on Azure and Kubernetes. You will take over services from Senior AI Engineers and ensure reliability, security and cost-efficiency, working with platform architects, other engineers, business content owners and IT operations.

The role requires 3–5 years of experience with Azure DevOps, AKS, Azure OpenAI, LangChain, Python, and RAG, plus fluency in English and Dutch or French.

Qualifications

• Experience operating or supporting an LLM application in production for 6+ months.
• Experience investigating quality issues or incidents using traces or logs.
• Experience running evaluations after model or prompt changes.
• Experience deploying Kubernetes workloads and Terraform via CI/CD on Azure.
• Fluent in English; native or bilingual in Dutch or French.

Responsibilities

• Operate AI services in production: monitor availability, latency and errors, manage incidents and requests.
• Maintain evaluation sets with content owners; monitor quality and user feedback.
• Operate ingestion pipelines and content connectors; monitor index health.
• Monitor agent integrations; review tool calls and handle timeouts.
• Manage model version upgrades, prompts, dependencies and security updates.
• Track run costs and propose optimisations; ensure cost-efficient operations.
• Maintain IaC artefacts (Terraform, Helm) and keep DEV/TST/ACC/PROD environments aligned.
• Ensure data protection: retention, erasure and access restrictions.
• Document runbooks and report service health to stakeholders.

Skills

LLM production experience

Python

Azure OpenAI Service

Kubernetes

LangChain

Azure DevOps

RAG

Monitoring & incident response

Cost optimisation

Education

Bachelor's degree or higher

Tools

Terraform

Azure Kubernetes Service

Azure DevOps

LangChain

Databricks

OpenTelemetry

MLflow

Job description

What you will do

A Belgian public transport company is building employee- and customer-facing AI services on an AI platform running on Azure and Kubernetes. The first services go live in December 2026, with more to follow in 2027. You will join the AI Centre of Excellence and own the Run phase of these AI services in production.

You will take over each service from the Senior AI Engineers who built it and keep it reliable, measured, secure and cost-efficient over time. You will work alongside the internal AI Platform Architect, two Senior AI Engineers, the business and content owners of each service, and the IT operations teams.

The AI Platform runs on a hybrid operating model: managed Azure services (Azure OpenAI Service, Azure AI Search, Azure API Management, Azure AI Content Safety) combined with self-hosted open-source components on Azure Kubernetes Service (agent orchestration in Python with LangChain, ingestion pipeline), with MLflow on Databricks for evaluation and tracing (OpenTelemetry). The AI Centre of Excellence team owns Infrastructure-as-Code for all application-scoped Azure resources, using Terraform and Azure DevOps pipelines.

Your activities will vary from service to service. Typicaly you will:

• 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
• Maintain runbooks and documentation, and report service health to service owners and the AI Centre of Excellence on a regular basis
• Deliver small enhancements and fixes; structural changes and new features stay with the Build team

What we are looking for

You have intermediate-level experience with the following technologies, all gained this year or recently:

• Azure DevOps
• Azure Kubernetes Service (AKS)
• Azure OpenAI Service
• LangChain
• LLM / Large Language Models
• Python
• RAG (Retrieval-Augmented Generation)
• Terraform
• Vector databases

You must be able to answer yes to the following questions and provide detailed examples:

• Have you personally operated or supported an LLM application (RAG, agent or document processing) in production for at least 6 months?
• Have you personally investigated a quality issue or incident in an LLM application or AI agent using traces or logs?
• Have you run or maintained evaluations of an LLM application, for example re-running test sets after a model or prompt change?
• Have you personally deployed changes to Kubernetes workloads (manifests or Helm charts) and Terraform code through CI/CD pipelines on Azure?

You are fluent in English and native or bilingual in Dutch or French.

The setting

This assignment runs for 12 months, starting on 4 January 2027. The work is hybrid, with on-site presence in Brussels required 2 to 3 days per week.

You can join us for this assignment as a freelancer or as an employee of HumanInTech. Same role, same team. If you join as an employee, your employment continues beyond this assignment. When it ends, we’ll work together to find your next assignment.

Location: Brussels, hybrid

Work address: Belgium

Employer / contracting party: HumanInTech

Applications close (Brussels time): November 16, 2026 at 1:00 AM

Engagement: Freelance or employed by HumanInTech

Working hours: Full-time

Experience: 3–5 years or more

Education: Bachelor's or more

Published: November 2026