AI Agentic Ops SRE – Hybrid – Bangalore (7‑12 yrs)

About the role

We are seeking an experienced AI Agentic Operations Site Reliability Engineer (SRE) to join a leading multinational client in Bangalore. The role focuses on building, monitoring, and maintaining autonomous AI agents that can plan, execute, and self‑heal infrastructure without human intervention.

Key responsibilities

• Deploy and manage autonomous AI agents that think, plan, execute commands, and self‑heal cloud infrastructure.
• Provide tier‑3 production support for critical AI pipelines and cloud services, minimizing downtime.
• Participate in on‑call rotations, troubleshoot live incidents, and lead root‑cause analyses.
• Leverage LLM agents to scan logs, correlate traces, and automatically generate incident post‑mortems.
• Implement continuous chaos‑testing agents that probe infrastructure and remediate discovered vulnerabilities.

Required profile

• 7+ years of relevant experience in SRE or observability engineering.
• Strong background in multi‑agent systems and AI/Gen‑AI technologies.
• Ability to join immediately and work in a hybrid model (3 days onsite).

Required skills

• Observability with LangChain, LangGraph, and LangSmith.
• Deep integration experience with Galileo and LangSmith for prompt tracing and latency monitoring.
• Expert management of Loki (logs), Grafana (dashboards), Tempo (traces), and Mimir/Prometheus (metrics).
• Hands‑on experience with AI/LLM pipelines and cloud infrastructure.

What we offer

• Hybrid work arrangement (3 days in‑office, Bangalore).
• Opportunity to work on cutting‑edge autonomous AI operations.
• Immediate start for the right candidate.