Principal ML Ops Engineer (EMEA Remote)
Core
Design and operate production-grade model serving infrastructure for AI/ML workloads, ensuring high availability, low latency, and cost-efficient inference systems.
Role type
Principal ML Ops Engineer (Infrastructure)
Builds
Scalable, reliable, and efficient ML inference platforms powering real-time AI applications
Domain
Cloud Computing / AI / European Deep-Tech SaaS
Deliverable
production ML models
Required skills
Model serving frameworks (vLLM, TGI, Triton), Container orchestration, GPU-based workload management, MLOps tooling, Python, Infrastructure-as-code (Terraform, Helm), Distributed systems, Performance tuning
Preferred skills
ML platforms (Kubeflow, MLflow, KubeAI), GPU scheduling, CUDA/ROCm optimization, Multi-tenant inference systems, Cost optimization, Greenfield infrastructure projects
Technologies
vLLM, TGI, Triton, Terraform, Helm, Python, Kubeflow, MLflow, KubeAI, CUDA, ROCm
Responsibilities
Build and operate production-grade model serving infrastructure; Design and implement robust deployment pipelines with blue/green and canary rollout strategies; Develop and maintain auto-scaling systems, multi-model serving architectures, and intelligent request routing layers; Optimize GPU utilization, memory efficiency, network throughput, and model artifact storage performance; Design observability systems for tracking inference latency, throughput, GPU usage, cost metrics, and system health; Manage model registries and CI/CD pipelines enabling automated and reproducible model deployments; Own the full lifecycle of ML systems from development through production, including operational support and on-call responsibilities; Define engineering best practices and contribute to platform scalability in a fast-moving startup environment