AI Engineer (m/f/d) – RAG, LLM & Retrieval Systems

We are looking for an AI Engineer with a focus on RAG (Retrieval-Augmented Generation) to build intelligent, context-aware AI systems.

You will work at the intersection of data, retrieval, and large language models, building systems that efficiently retrieve relevant information and turn it into high-quality responses.

This position is remote within Germany.

• Build and optimize RAG systems
• Develop retrieval pipelines (embeddings, vector search, ranking)
• Integrate LLMs (e.g., OpenAI and other models)
• Process and structure data sources (documents, APIs, databases)
• Improve response quality, relevance, and contextual understanding
• Develop strategies for chunking, indexing, and query optimization
• Evaluate and test AI outputs
• Collaborate with backend and frontend teams to integrate AI features

• Experience in AI, machine learning, or NLP
• Experience with LLMs and API-based AI systems
• Understanding of RAG architectures
• Experience with vector databases or similarity search
• Knowledge of Python or TypeScript / Node.js
• Experience with data processing and APIs
• Analytical and structured mindset

• Experience with LangChain, LlamaIndex, or similar frameworks
• Experience with embedding models
• Experience with ranking or re-ranking approaches
• Experience working with large datasets or knowledge bases
• Experience with AI evaluation or prompt engineering
• Understanding of scalable systems and performance optimization

• LLM APIs (e.g., OpenAI)
• Vector databases (e.g., Pinecone, Weaviate, Qdrant)
• Node.js / TypeScript or Python
• APIs and data pipelines
• Next.js (integration)
• AI / NLP frameworks

• Work on an innovative AI product
• Direct impact on core platform features
• Remote-first culture
• Flexible working hours
• Small teams with high ownership
• Room for experimentation and innovation