Senior AI Engineer

Function

We're looking for an experienced Senior AI Engineer to join our client's team and help transform innovative AI concepts into robust, production-ready solutions. You'll play a key role in developing and stabilising advanced AI services that support both internal users and external audiences. Working alongside AI architects, senior engineers, and multidisciplinary teams, you'll take ownership of the technical delivery of complex AI applications, with a strong focus on reliability, security, performance, and long-term maintainability.

Key Responsibilities

• Design and develop end-to-end Retrieval-Augmented Generation (RAG) solutions, from information retrieval and document processing to context management and answer generation.
• Build and maintain data ingestion pipelines, including connectors, document chunking, embedding generation, and incremental data refresh.
• Implement document-level access controls and security mechanisms to ensure that AI-generated responses respect user permissions.
• Develop agent orchestration workflows, prompt templates, and guardrails to improve the reliability and safety of AI applications.
• Design and implement evaluation frameworks using offline test sets, retrieval metrics, answer-quality measurements, and end-to-end tracing.
• Prepare production deployment assets using Terraform, Helm, Kubernetes manifests, and Azure DevOps pipelines.
• Implement observability and cost-monitoring mechanisms covering latency, token consumption, operational costs, and performance regressions following model or prompt changes.
• Support early production deployments through incident analysis, performance tuning, troubleshooting, runbook creation, technical documentation, and operational handover.
• Collaborate with architects and engineering teams to ensure that AI services meet production standards for scalability, security, quality, and operational efficiency.

Your Profile

• Proven senior-level experience designing, building, or leading production-grade AI solutions, particularly RAG-based applications.
• Strong hands-on expertise in Python, Large Language Models (LLMs), LangChain, and vector databases.
• Experience with Microsoft Azure AI services, including Azure OpenAI Service and Azure AI Search.
• Practical experience deploying and managing containerised applications using Azure Kubernetes Service (AKS), Kubernetes manifests, and Helm charts.
• Solid knowledge of infrastructure as code and automated delivery pipelines, particularly Terraform and Azure DevOps.
• Experience designing evaluation frameworks for RAG or LLM applications, including retrieval quality, answer accuracy, and regression testing.
• Understanding of identity management, document-level security, and access control propagation in AI-powered information retrieval systems.
• Familiarity with AI service observability, tracing, content safety, API management, and model lifecycle tooling such as MLflow.
• A strong sense of ownership, analytical thinking, and the ability to work independently while collaborating effectively with technical stakeholders.

Practical Information

• Location: Brussels.
• On-site presence: 2 to 3 days per week.
• Languages: Dutch or French, together with English.

If you're passionate about building production-ready generative AI solutions and enjoy tackling the technical challenges of moving from experimentation to reliable delivery, this is an excellent opportunity to make a tangible impact on the next generation of enterprise AI services.

Contactperson & Reference

• Reference #: INW28366
• Pieter Messely
• pieter.messely@i4m.be