The Maffia and a media company are looking for a freelance AI Native Engineer.

Your role

Develop and maintain the internal AI platform, mainly in Go, with a focus on distributed services, event-driven architecture and message-based communication.
Build secure AI integrations by connecting LLM providers, self-hosted models and external tools via APIs and the Model Context Protocol (MCP).
Implement identity and governance mechanisms, including OAuth2, OIDC, secrets management, audit logging and policy-based access controls.
Set up self-service capabilities so that internal teams can connect their own tools, workflows and AI agents without involvement from the platform team.
Develop and optimise the model infrastructure by integrating multiple AI providers and self-hosted models, taking performance, cost and data sensitivity into account.
Manage deployments and platform operations, including Linux containers, configuration management, release processes, monitoring and rollback procedures.
Contribute to architectural and technical decisions, document designs and decisions through Architecture Decision Records (ADRs) and safeguard consistent engineering standards.
Collaborate with internal stakeholders and integrate the platform with workflow automation, desktop assistants and other business applications.
Work in a hybrid setup, with at least two days per week in the office in Antwerp.

Your profile

You are a mid-level or senior engineer with solid experience in backend development and distributed systems, preferably with Go (Golang).
You understand how event-driven architectures and message-based services work in production.
You have experience with authentication and security technologies such as OAuth2, OIDC, token management and encryption.
You are familiar with Linux environments, containers and modern deployment practices.
Ideally, you have already worked with LLM APIs, tool calling, streaming or MCP integrations.
You translate technical designs into reliable production solutions, document architectural decisions and take ownership of your work from design to delivery.
You are analytical, structured and enjoy working in a small, autonomous engineering team.
You communicate effectively in Dutch and English.
A plus: experience with GPU-based model serving, workflow automation, observability, audit pipelines or platform engineering.