Summary

This senior SRE role keeps Runware's distributed AI infrastructure reliable, performant, and resilient across production services and GPU-backed workloads. It is fully remote, with core collaboration hours, and focuses on observability, incident response, automation, capacity planning, and long-term reliability improvements.

Responsibilities

• Own reliability of critical production services
• Define SLIs, SLOs, and alerting standards
• Investigate incidents across distributed production systems
• Lead incident reviews and root cause analyses
• Automate remediation and reduce operational toil
• Plan capacity, performance, and platform scaling