Pragmatike logoPragmatike logo

AI Infrastructure Engineer (GPU) - Remote EMEA

PragmatikeUkraine
Remote Full-time

Clicking Apply Now takes you to AutoApply where you can tailor your resume and apply.


Experience Level

Mid to Senior

Qualifications

Proven experience in AI infrastructure and model serving. Familiarity with GPU architecture and distributed systems. Strong problem-solving skills and ability to work independently.

About the job

Location: Remote within EMEA time zones, including Ukraine
Start date: ASAP
Languages: Fluent English required
Industry: Cloud Computing, AI, European Deep-Tech SaaS

Role overview

Pragmatike is a funded startup developing distributed cloud infrastructure for AI and machine learning workloads. The team focuses on GPU-powered platforms, secure storage, and high-speed data transfer, using a decentralized approach to reduce the environmental impact of cloud computing compared to traditional providers.

This is a hands-on engineering position centered on designing, building, and managing the core infrastructure needed for scalable machine learning model serving. The work supports real-time AI applications and involves close collaboration with infrastructure, platform, and applied AI teams. Success in this role requires a strong sense of ownership, a production mindset, and experience working with distributed GPU systems.

What you will do

  • Build and maintain production-ready model serving systems using frameworks such as vLLM, TGI, Triton, or similar technologies.
  • Design deployment pipelines that use blue/green and canary rollout strategies for machine learning models.
  • Develop auto-scaling mechanisms, multi-model serving capabilities, and request routing layers.
  • Optimize GPU usage, memory management, network throughput, and storage performance for model artifacts.
  • Implement observability tools to monitor inference latency, throughput, GPU utilization, costs, and system health.
  • Manage model registries and CI/CD pipelines to support automated and reproducible deployments.
  • Oversee the full lifecycle of machine learning systems, from development to production, including operational support and on-call duties.
  • Help define engineering best practices and contribute to platform scalability as the company grows.

Requirements

  • Direct experience with AI infrastructure and model serving in production environments.
  • Knowledge of GPU architecture and distributed systems.
  • Strong problem-solving skills and the ability to work independently.

About Pragmatike

Pragmatike is a pioneering startup dedicated to transforming how cloud infrastructure is utilized for AI and machine learning workloads, focusing on sustainability and efficiency.

Similar jobs

Browse all companies, explore by city & role, or SEO search pages. View directory listings: all jobs, search results, location & role pages.

Tailoring 0 resumes

We'll move completed jobs to Ready to Apply automatically.