AI Platform Engineer (m/w/d)
Core
Designing and implementing end-to-end GenAI and ML infrastructures to support the full lifecycle of AI applications, from data preparation to model deployment and monitoring.
Role type
Senior IC AI Platform Engineer (GenAI/ML Infrastructure)
Builds
Production-ready GenAI and ML platforms, local LLMs, and model-as-a-service solutions for enterprise clients.
Domain
Consulting, Generative AI, Machine Learning, Cloud Infrastructure
Deliverable
production ML models | infrastructure
Required skills
Kubernetes, Docker, container orchestration, Python, Linux, Terraform, Ansible, Git, CI/CD pipelines, LLM fine-tuning (LoRA, Prompt Tuning), model deployment (vLLM, Hugging Face, NVIDIA AI Enterprise), cloud platforms (AWS, Azure, GCP, IBM Cloud)
Preferred skills
Experience in public sector IT landscapes, large-scale IT organization management
Technologies
Kubernetes, Docker, Openshift, Hugging Face, NVIDIA AI Enterprise, vLLM, LangChain, Python, Ansible, Terraform, Git, Jenkins, AWS, Azure, Google Cloud, IBM Cloud
Responsibilities
Conceive and implement end-to-end GenAI/ML infrastructures covering the full application lifecycle; plan, build, and administer operational platforms (on-premise or cloud); deploy local LLMs and GenAI models with tool/API integration; support Data Scientists and Engineers in workflow creation; provide client consulting from requirements to production; ensure project quality and portfolio development.
Seniority
Senior, hands-on IC