3 months ago
Antwerp, BelgiumMid Level
Responsibilities
- Design, build, deploy, scale, and operate production-grade generative AI systems.
- Develop autonomous agents and conversational systems that interact with external tools and APIs.
- Build and optimize RAG pipelines connecting enterprise data sources to LLMs.
- Perform prompt and context engineering to improve quality, reduce hallucinations, and manage conversational state.
- Evaluate AI system quality using generative AI metrics, coherence tests, and production monitoring.
- Build and maintain model deployment automation, CI/CD pipelines, and automated testing.
- Monitor production model performance, including drift detection and quality metric tracking.
- Manage production updates to libraries, models, and dependencies while ensuring versioning, reproducibility, and safe rollouts.
- Collaborate with ML engineers, developers, DevOps, and infrastructure teams.
Requirements
- 3 to 5 years of experience in AI/ML engineering or related fields.
- Solid understanding of LLM fundamentals, including transformers, attention mechanisms, generation parameters, and fine-tuning approaches.
- Hands-on experience with LLMs, agents, RAG pipelines, production deployment, and MLOps.
- Experience with Python, OpenAI API, Hugging Face Transformers, LangChain, LangGraph, Langfuse, FastAPI or Flask, Docker, Kubernetes, and AWS services.
- Fluent communication in Dutch and English, or Dutch, English, and French.
- Strong problem-solving, algorithmic creativity, collaboration, communication, autonomy, curiosity, and incident-handling skills.
- Experience with TypeScript and AI-assisted development tools such as Cursor, Claude Code, Windsurf, or Copilot is a bonus.
Benefits
- Flexible working with trust, space to perform, and room to take ownership.
- Collaborative, human-sized environment with strong team spirit.
- Opportunities to learn, continuously develop skills, and work on AI solutions across various industries.
- Potential to grow toward a Team Lead position over time.
