🛠 Tech Stack

💼 About This Role

You'll join an award-winning tech community in Amsterdam, designing and deploying LLM-powered applications from backend to frontend. You'll work with cutting-edge LLM technologies across RAG pipelines, vector databases, and cloud deployment. Collaborate with cross-functional teams to solve real human problems with a holistic approach.

🎯 What You'll Do

• Design and implement end-to-end LLM-enabled applications from backend to frontend
• Integrate commercial and open-source LLMs via APIs or fine-tuning
• Build RAG pipelines with embeddings, vector databases, and prompt engineering
• Collaborate with client teams to choose suitable AI technologies

📋 Requirements

• Experience deploying AI applications in cloud environments with Docker/Kubernetes
• Foundational knowledge of DevOps including CI/CD and test automation
• Experience with vector databases like pgvector, ChromaDB, or Pinecone
• Proficiency in Python or Node.js/TypeScript and frameworks like LangChain or FastAPI

✨ Nice to Have

• Awareness of data privacy (GDPR) and ethical AI considerations
• Dutch language skills

🎁 Benefits & Perks

• 🏖️ Flexible work with impact on approach and technologies
• 📚 Professional growth through training courses and community events
• 🏠 Work-life balance support including moving day and child care services
• 🎉 300+ hobby clubs from winter swimming to archery