Summary

Staff/senior DevOps Engineer responsible for building, operating, and scaling Runware's global AI inference infrastructure across GPU fleets, bare-metal servers, and containerised production systems. This is a fully remote role focused on reliability, automation, observability, security, incident response, and high-performance platform operations.

Responsibilities

• Build infrastructure for real-time ai inference
• Scale gpu fleets and bare-metal servers
• Automate provisioning and deployment workflows
• Improve observability across production systems
• Respond to incidents and debug failures
• Strengthen infrastructure security and compliance
• Manage capacity for traffic and model demand