LLM Inference Platform Architect
Posted Updated
Description
QuTwo, Europe’s private Quantum AI Lab, seeks an LLM Inference Platform Architect to design and lead a secure internal serving platform on GPU hardware. You will manage GPU clusters, inference engines, access control, and capacity planning to deliver a reliable AI service across the organization.
Collaborating with security, operations, and LLM scientists, you will set platform standards, ensure regulatory compliance (including DORA), and deploy optimized models while maintaining strict data
Design and lead a secure, internal LLM serving platform on GPU hardware. Manage the full serving stack: GPU clusters, inference engines, access control, capacity planning. Set platform standards and ensure regulatory compliance (e.g., DORA). Partner with security, operations, and LLM scientists to deploy optimized models. Experience designing and running large-scale infrastructure on Kubernetes with GPU workloads. Hands-on experience with LLM inference engines (vLLM, SGLang, TensorRT-LLM or similar). Infrastructure as code (Terraform or similar), CI/CD and observability tooling. Understanding of security, identity and network design in enterprise environments. Experience writing architecture guidelines and working with enterprise architecture teams.Skills
Sign in to read and join the discussion.