ML Ops Engineer (EMEA Remote)

📋 Description

• • ML Ops Engineer responsible for building and operating production-grade model serving infrastructure for AI-native cloud services, focusing on scalable, reliable, and efficient inference systems for GPU-powered workloads.
• • Day-to-day tasks include designing deployment pipelines with blue/green and canary strategies, optimizing GPU utilization and network throughput, developing auto-scaling systems, managing model registries and CI/CD pipelines, and implementing observability for latency, throughput, and cost metrics.
• • Part of a fast-scaling, well-funded distributed cloud infrastructure startup building next-generation AI-native cloud services with a decentralized architecture that reduces environmental impact compared to traditional providers.
• • Opportunity to own the full lifecycle of ML systems, influence core engineering decisions, define platform best practices, and gain deep expertise in next-generation AI infrastructure while working on greenfield projects in a high-growth startup environment.