AI Infrastructure Engineer (GPU) - Remote EMEA
Pragmatike · Remote · Ukraine · Czech Republic · Bulgaria · Latvia · Spain · Hungary · Albania · Lithuania · Greece · Bosnia & Herzegovina · Croatia · Estonia · Serbia · Poland · Armenia · Portugal · Italy · Malta · Türkiye · Montenegro · Romania ·
COMPENSATION
€•• – ••k
Listed on the employer's job board (Ashby)
- Fully remote (EMEA)
- GPU Infrastructure
- Python + Terraform
- Senior Level
- Fluent English
Join a well-funded startup redefining compute delivery through decentralized, GPU-powered cloud services. You will build and maintain production-grade infrastructure for machine learning model serving, ensuring high availability and low latency. This hands-on position involves close collaboration with platform and applied AI teams to optimize performance and cost efficiency.
What you'll do
- Build and operate model serving infrastructure using frameworks like vLLM or Triton
- Design deployment pipelines with blue/green and canary rollout strategies
- Develop auto-scaling systems and intelligent request routing layers
- Optimize GPU utilization, memory efficiency, and network throughput
- Create observability systems for tracking latency, throughput, and costs
- Manage model registries and CI/CD pipelines for automated deployments
- Own the full lifecycle of ML systems including operational support
- Define engineering best practices for platform scalability
What you'll need
- 4+ years in ML Ops, Platform Engineering, or SRE for ML systems
- Hands-on experience with vLLM, TGI, Triton, or equivalent frameworks
- Strong background in container orchestration and GPU workloads
- Experience with MLOps tooling, model registries, and experiment tracking
- Proficiency in Python and infrastructure-as-code tools like Terraform
- Understanding of distributed systems and production reliability
- Ability to use AI coding assistants for development workflows
- Ownership mindset for independent work in a remote environment
Nice to have
- Experience with Kubeflow, MLflow, or KubeAI platforms
- Knowledge of GPU scheduling and CUDA/ROCm optimization
- Experience with cost optimization across GPU types
- Background in early-stage startups or greenfield projects
- Proven experience building production systems from scratch
Stack
- vLLM
- TGI
- Triton
- Python
- Terraform
- Helm
- Kubeflow
- MLflow
- CUDA
- ROCm
How you'll work
- Fully remote position
- Must be in EMEA timezone
- On-call responsibilities included