Full-Stack AI Engineer – HR & Business Services

Our client, a leading provider of HR and business solutions, is seeking an engineer to build AI-native features for their modern TypeScript stack. This role involves owning features end-to-end, from prompt design through to scalable infrastructure for production AI systems.

• Design and ship full-stack features using React, Node.js, and TypeScript from discovery through to production.
• Write and maintain production prompts, including versioning, regression testing, and observability.
• Architect and operate scalable infrastructure for high-availability AI applications, managing latency and cost.
• Integrate and orchestrate multiple AI providers such as Azure OpenAI, Gemini, and Anthropic.
• Build agentic and tool-using systems using MCP and A2A patterns where they fit the project needs.
• Model and query data across MongoDB and PostgreSQL databases to suit specific use cases.
• Maintain high engineering standards through code reviews, pairing, and the implementation of AI guardrails.

• 5+ years of professional full-stack engineering experience with React, Node.js, and TypeScript.
• 3+ years experience designing, deploying, and operating scalable, high-availability infrastructure.
• 3+ years hands-on experience with prompt engineering, including iteration based on real usage and evaluation.
• 3+ years production experience with at least one major LLM provider such as Azure OpenAI, Google Gemini, or Anthropic.
• 3+ years expertise in data modeling and querying using both MongoDB and PostgreSQL.
• 3+ years working knowledge of MCP, A2A, and AI skills.
• You're proficient in using Tailwind CSS for production frontend work.
• You possess a deliberate approach to using AI for engineering acceleration and code quality.
• You are fluent in Dutch and English.

Nice to Haves

• Experience building agentic systems, tool-use orchestration, or multi-agent workflows.
• Background in evaluation frameworks for LLM outputs and regression suites.
• Knowledge of vector databases, RAG architectures, or retrieval pipelines at scale.
• Cloud infrastructure experience specifically on Azure.
• Contributions to open-source AI tooling or the MCP/A2A ecosystem.

• Start date: ASAP
• Location: Bruges
• Working model: Hybrid
• Contract: open to both permanent employees and freelancers