CareerPlan

AI Infrastructure Engineer (GPU) - Remote EMEA

UkraineRemoteFull-time2026-09-23 → 2026-11-19
Remote · from EMEA

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

Senior IC AI Infrastructure Engineer (GPU)

Builds

Scalable, reliable ML inference platforms and distributed GPU systems

Domain

Cloud Computing / AI / European Deep-Tech SaaS

Deliverable

production ML models

Required skills

Model serving frameworks (vLLM, TGI, Triton), Container orchestration, GPU 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 strategies; Develop auto-scaling systems and intelligent request routing; Optimize GPU utilization, memory efficiency, and network throughput; Design observability systems for inference metrics; Manage model registries and CI/CD pipelines; Own the full lifecycle of ML systems from development through production.

Seniority

Senior, hands-on IC