AI Engineer – Generative AI, LLMs & RAG

Salt; Brussel; On-site; EUR 111,000 - 166,000; Full time

Job summary

Salt is seeking an experienced AI Engineer for a 12-month freelance assignment with a major Belgian federal public-sector organisation. You will build and deploy AI services, agents and RAG solutions, integrating LLMs into secure enterprise applications while ensuring reliability, cost effectiveness and governance.

The role is hands-on and requires strong software development skills, practical AI implementation experience and collaboration with AI architects, security and data teams to deliver

Qualifications

• 5-8 years of software/ML engineering experience.
• Strong programming skills in Python and Java.
• Hands-on experience with LLMs, embeddings, RAG, AI agents and model APIs.
• Experience building and integrating APIs, authentication and containerised apps.
• Familiarity with Git, CI/CD pipelines, IaC and production monitoring.
• Knowledge of security, privacy, and governance in AI deployments.
• Experience delivering end-to-end AI solutions in enterprise environments.
• Experience in the Belgian public sector or regulated settings.

Responsibilities

• Design, develop and implement AI services, agents and RAG solutions.
• Build reusable components for model access, prompting and context management.
• Integrate AI capabilities into existing enterprise applications and data platforms.
• Develop automated testing, evaluation frameworks and observability.
• Implement CI/CD and MLOps practices for production deployment.
• Collaborate with cross-functional teams to deliver secure, scalable AI solutions.

Skills

Python

Java

LLMs

RAG

MLOps

CI/CD

Git

Security

Cloud

Tools

APIs

Containerisation

IaC

Observability

Job description

We are seeking an experienced AI Engineer to join a major Belgian federal public-sector organisation on an initial 12-month freelance assignment.

This is an exciting opportunity to contribute to the development and implementation of Generative AI, Large Language Models (LLMs), AI Agents and Retrieval-Augmented Generation (RAG) solutions within a complex enterprise environment.

The successful candidate will be responsible for building, testing, deploying and maintaining the technical components that enable AI adoption across the organisation.

Working alongside AI Architects, software engineers, data specialists and security teams, you will help transform innovative AI concepts into secure, scalable and production-ready solutions that deliver tangible business value.

This is a hands-on engineering role, suited to someone with strong software development skills and practical experience implementing modern AI technologies.

Key Responsibilities

AI Development & Integration

• Design, develop and implement AI services, agents, RAG solutions and API integrations.
• Build reusable components for model access, prompting, context management and error handling.
• Integrate LLMs and AI capabilities into existing enterprise applications and data platforms.
• Support AI experimentation, technical prototypes and proofs of concept.

Testing, Evaluation & Reliability

• Develop automated testing and evaluation frameworks to assess AI quality, accuracy, safety, performance and cost.
• Implement logging, monitoring, observability and cost-tracking capabilities.
• Troubleshoot production issues and improve solutions using logs, evaluation results and user feedback.
• Ensure AI services are reliable, maintainable and operationally efficient.

MLOps, LLMOps & Production Deployment

• Implement CI/CD and MLOps/LLMOps practices covering version control, deployment, configuration and rollback.
• Support the transition of AI applications from sandbox environments into production.
• Work with cloud and container platforms to deploy and maintain AI solutions.
• Ensure solutions comply with established architecture, security and governance requirements.
• Work with data and platform teams to implement secure data flows and integrations.
• Apply privacy, security and operational reliability principles throughout development.
• Produce technical documentation, runbooks and reusable implementation examples.
• Collaborate with architecture, security, business and engineering teams to deliver practical AI solutions.
• 5-8 years' experience in software engineering, platform engineering, machine learning engineering or a comparable hands-on technical role.
• Strong programming skills, preferably Python and Java.
• Practical experience working with LLMs, embeddings, RAG, AI agents and model APIs.
• Experience developing and integrating APIs, authentication mechanisms and containerised applications.
• Strong knowledge of Git, CI/CD pipelines, automated testing and Infrastructure as Code (IaC).
• Experience with MLOps/LLMOps, deployment automation and production monitoring.
• Familiarity with cloud or container platforms and observability tools.
• Understanding of AI evaluation methods, including quality, reliability, safety, performance and cost.
• Strong awareness of security, privacy, documentation and operational best practices.
• Experience delivering technical solutions from development through to production.
• Experience working within the Belgian public sector or regulated environments.
• Knowledge of Belgian G-Cloud or OISZ (Public Institutions of Social Security).
• Experience building reusable enterprise AI components or AI platform services.
• Previous involvement in production GenAI, RAG or agent-based AI implementations.

Personal Skills

We are looking for someone who is technically curious, innovative and solutions-oriented, with strong analytical and problem-solving skills.

You should be comfortable collaborating with multidisciplinary teams, explaining technical concepts clearly and taking ownership of high-quality deliverables.

Join a forward-thinking AI initiative and help develop secure, scalable and production-ready AI solutions that will support the digital transformation of essential public services.