AI Engineer / KI-Entwickler – LLM & RAG (m/w/d)
Core
Develop and deploy LLM applications (assistants, document pipelines, agents) and RAG architectures for clients, integrating unstructured document processing and backend services.
Role type
Senior AI Engineer (LLM & RAG)
Builds
Production-ready LLM applications, RAG pipelines, and reusable reference architectures
Domain
Enterprise AI, Large Language Models, Document Processing
Deliverable
production ML models
Required skills
Python, Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), Vector Databases, SQL, Cloud Platforms (Azure/AWS/GCP), Containerization, CI/CD
Preferred skills
Healthcare domain knowledge, Agentic AI, DevSecOps, Kubernetes, Terraform, Azure Document Intelligence
Technologies
LangChain, Python, SQL, Azure, AWS, Google Cloud, Kubernetes, Terraform
Responsibilities
Design and implement RAG architectures with chunking and embedding; build pipelines for text recognition and document structuring; integrate AI components via backend services; evaluate model trade-offs (quality, cost, latency, privacy); create reusable reference architectures
Seniority
Senior, hands-on IC
