Cloud Site Reliability Engineer
AI Tools & Frameworks
Tech Stack
Agent Workflow
Uses "traditional and in-house LLM-based AI tools/MCP" as part of the SRE toolkit. Role involves designing agentic triage software.
About the Role
Ford seeks an experienced and passionate Site Reliability Engineer (SRE) to join their team. The role focuses on designing and enhancing agentic triage software across the organization to enable automated responses and reduce response times (MTTX). Key responsibilities include ensuring system reliability and scalability while collaborating with a global SRE team in a culture emphasizing continuous improvement. The position involves hands-on contributions to infrastructure supporting millions of devices. Tech stack: Python, Go, Kubernetes, Dynatrace, OpenTelemetry, GCP, and traditional and in-house LLM-based AI tools/MCP. The posting notes the recruiter previously hired candidates through Hacker News. No visa sponsorship provided.