Senior Infrastructure Engineer in Praha

Join MasterDC’s Enterprise Innovation team as we develop groundbreaking infrastructure powering critical systems for ČEZ Domat, Ušetřeno.cz, Czech Republic’s established (since 2018) AI service provider and others. You’ll help implement our upcoming Inference-as-a-Service cloud platform, build managed GPU server services for enterprise customers, and contribute to our strategic migration from VMware to a fully open-source cloud solution—all while working with production Kubernetes clusters, distributed systems at scale, and hparticipating in building Czech Republic’s first dedicated AI datacenter launching in 2026.

• Develop our Inference-as-a-Service platform using Kubernetes, implementing GPU orchestration and model serving infrastructure that will power AI workloads for enterprise clients across financial services and e-commerce sectors
• Engineer and automate distributed systems spanning databases, application servers, load balancers, and web services across our Prague and Brno datacenters with 100GbE network backbone
• Drive the open-source cloud transformation, replacing VMware infrastructure with FOSS and cloud-native solutions while maintaining 99.99% SLA for enterprise clients
• Build GitOps workflows and CI/CD pipelines using Terraform, Ansible, and ArgoCD to enable infrastructure-as-code practices that reduce deployment time from hours to minutes
• Collaborate directly with enterprise clients from financial institutions and e-commerce platforms to understand their infrastructure needs and implement solutions—no anonymous ticketing systems here
• Support production systems through on-call rotation (approximately one day every 8-10 days based on team availability) with comprehensive runbook support and proper jcompensation for after-hours work

• 4+ years in infrastructure engineering, DevOps, or SRE roles with production systems
• Strong Linux administration skills (RHEL/Debian/Ubuntu) including performance tuning and troubleshooting
• Production Kubernetes experience including cluster management, networking, and storage • Hands-on experience with distributed systems (databases, message queues, microservices)
• Infrastructure-as-code expertise with Terraform, Ansible, or similar tools
• Programming skills in Python or similar languages for automation and tooling

• Experience with AI/ML infrastructure, GPU clusters, or model serving platforms
• Background in financial services or high-compliance environments
• Open-source virtualization platforms (Proxmox, KVM, Cloudstack)
• Certifications: CKA, RHCE, or cloud provider certifications

• Competitive compensation aligned with Czech market standards for senior infrastructure roles
• 5 weeks vacation (standard in Czech tech) plus 5 days for each 5 years with the company.
• Professional development budget for certifications and conferences
• Hybrid or remote work arrangement
• Multisport card and comprehensive health benefits
• Opportunity to shape Czech Republic’s first dedicated AI datacenter