Senior SRE / Platform Engineer, building and operating scalable infrastructure for large-scale platforms.
10+ years turning infrastructure into reliable, observable, and automated systems across cloud, containers, programing and service meshes.
Experienced in Agentic AI Engineering, designed and built an internal agentic AI platform on top of HolmesGPT, enabling autonomous incident investigation and root-cause analysis at scale. The platform integrates LLM orchestration, MCP (Model Context Protocol) servers, Slack, and Kubernetes tooling to deliver AI-driven on-call assistance with minimal human intervention.
Orchestration & Service Mesh
Cloud & IaC
Observability
CI/CD
AI & LLM
Languages


