KI-Engineer*in (all genders) – LLM-Infrastruktur und KI-Plattform
Core
Operating and evolving the central LLM gateway and AI services for research and administration, ensuring secure and efficient deployment of modern AI technologies.
Role type
Senior IC Machine Learning Infrastructure Engineer (LLM Ops)
Builds
Central LLM gateway, RAG systems, and AI service endpoints for internal research use cases
Domain
AI Infrastructure / Large Language Models / Research Computing
Deliverable
production ML models | infrastructure
Required skills
Python programming, LLM usage and API integration, Docker, Kubernetes, Cloud platforms (AWS/Azure), RAG architectures, Vektordatabases, LLMOps processes, Prompt Engineering, Information security
Preferred skills
Fine-tuning, Embeddings, API/Gateway technologies (REST, LiteLLM, Kong), Coding-Agent tools
Technologies
AWS Bedrock, Azure, FAISS, Qdrant, Weaviate, LiteLLM, Kong, Docker, Kubernetes
Responsibilities
Operate and provision LLM endpoints in cloud and local environments; Implement access control and authentication for AI services; Establish monitoring, observability, and incident handling for AI services; Evaluate and benchmark LLMs to ensure quality and security; Develop LLMOps processes for automated deployments and versioning; Support research groups in evaluating AI use cases and technical feasibility; Build internal knowledge through workshops and documentation; Monitor market developments and support licensing/contract negotiations
Seniority
Mid-Senior, hands-on IC
