AI Engineer / KI-Entwickler – LLM & RAG (m/w/d)
Core
Build and deploy customer-facing applications using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) to process unstructured documents and automate tasks.
Role type
Senior AI Engineer (LLM & RAG)
Builds
RAG architectures, document processing pipelines, and backend services integrating AI components into client systems.
Domain
Artificial Intelligence / Healthcare / Consulting
Deliverable
production ML models
Required skills
Python, LLMs (Prompt Engineering, RAG), Vector Databases, SQL, Cloud Platforms (Azure/AWS/GCP), Containerization, CI/CD
Preferred skills
Healthcare domain knowledge, Document Intelligence, Agentic AI, DevSecOps, Kubernetes, Terraform
Technologies
LangChain, Azure Document Intelligence, Kubernetes, Terraform
Responsibilities
Develop LLM applications (assistants, pipelines, agents) from concept to production; Build RAG architectures with chunking, embeddings, and retrieval; Process unstructured documents via OCR, extraction, and summarization pipelines; Integrate AI components with client systems via backend services; Evaluate and recommend appropriate models based on quality, cost, and latency; Create reusable reference architectures.
Seniority
Senior, hands-on IC