Drimva

Speakeasy

Platform Engineer (SRE) - AI Control Plane

San Francisco · On-site · Full-time · Posted May 29, 2026

About the job

Improve the reliability, performance, and availability of Speakeasy’s AI control-plane platform by building operational processes and monitoring, and responding to production incidents.

What you'll do

  • Identify and implement architectural improvements to reliability, performance, and availability; foster a culture of reliability.
  • Design and implement deployments, upgrades, rollbacks, and postmortem review processes.
  • Build monitoring systems, debug production issues, and participate in on-call incident response.

What they ask for

  • Record of improving a product’s reliability and uptime.
  • Ability to work across the stack, from backend to frontend, and learn new frameworks.
  • Ability to participate in on-call rotation and respond to production incidents.
  • Ability to work in person in the San Francisco Office.

AI focus

Operate and improve reliability of an enterprise AI control-plane platform that manages access to MCPs, Skills, and Assistants.

Model-written summary · the original posting is authoritative

First seen Oct 29, 2026 · Last verified Nov 5, 2026 (UTC)