ML Ops Engineer (EMEA Remote)

Pragmatike is recruiting for a distributed cloud infrastructure startup seeking an ML Ops Engineer to build and operate production-grade model serving infrastructure for real-time AI applications. Responsibilities include designing deployment pipelines (blue/green, canary), auto-scaling, multi-model serving, intelligent request routing, optimizing GPU utilization and memory, observability for latency/throughput/cost, managing model registries and CI/CD, and on-call support. Required: 4+ years in MLOps/Platform/SRE, experience with vLLM/TGI/Triton, container orchestration for GPU workloads, MLOps tooling, Python and IaC (Terraform/Helm), and distributed systems expertise.