Principal ML Ops Engineer (EMEA Remote)

📋 Description

• Build and operate prod-grade model serving infra (vLLM, TGI, Triton)
• Design deployment pipelines with blue/green and canary rollouts
• Develop auto-scaling systems and multi-model serving architectures
• Optimize GPU utilization, memory, and network throughput
• Design observability for latency, throughput, GPU usage, and cost
• Manage model registries and CI/CD for automated deployments

🎯 Requirements

• 4+ years in ML Ops, Platform Eng, SRE, or similar ML infra roles
• Hands-on with model serving frameworks such as vLLM, TGI, Triton
• Strong container orchestration background and GPU-based production workloads
• Experience with MLOps tooling (registries, experiment tracking, pipelines)
• Python proficiency and IaC skills (Terraform, Helm, or similar)
• Strong understanding of distributed systems and reliability engineering

🎁 Benefits

• Take ownership of infrastructure powering a rapidly scaling AI cloud platform
• Build ML inference systems from the ground up in a high-growth startup
• Work at the intersection of distributed systems and GPU computing
• Gain deep expertise in next-gen AI infrastructure and model serving
• Influence core engineering decisions and scalable best practices