We are seeking an experienced MLOps Engineer – Edge AI Specialist to lead the design and deployment of on‑premise inference infrastructure for industrial vision systems. The role involves architecture of hybrid edge/cloud solutions, model optimization for embedded GPUs, CI/CD pipeline development, fleet management, and compliance with GDPR. The ideal candidate has 3‑5 years of production experience, expertise in TensorRT, ONNX, Kubernetes, and Python, and a strong background in real‑time analytics and GPU performance profiling.