AI/KI Platform Engineer (m/w/d)
Core
Develop, operate, and scale an AI-hosting platform where developers, agencies, and freelancers deploy AI applications using open-source models on modern GPU clusters.
Role type
Senior Platform Engineer (AI Infrastructure)
Builds
Managed AI-hosting and Dedicated AI-hosting services for customers
Domain
AI Infrastructure / GPU Clusters / LLM Hosting
Deliverable
infrastructure
Required skills
LLM fundamentals, Transformer architecture, Kubernetes, Python, Go, Docker, PostgreSQL, MongoDB, MySQL, Pandas, NumPy, JupyterLab
Preferred skills
vLLM, LiteLLM, Ollama, CUDA, GPU hardware, NVIDIA drivers, RAG, Embeddings, Vektordatenbanken, LoRA, Tool Calling, MCP
Technologies
Kubernetes, GPU Clusters, LLMs, Open-Source Models
Responsibilities
Ensure reliable, performant, and scalable delivery of AI applications; Operate the AI-hosting platform from Kubernetes to GPU clusters and LLM inference; Evaluate new models, frameworks, and AI technologies; Deploy AI models for customers; Design and implement software architectures.