Source description
About the role
Role : AI Agentic Ops SRE: Location: Bangalore Exp: 7 to 10 years Mission: Deploy autonomous AI agents that can think, plan, execute commands, and self-heal infrastructure. Provide tier-3 production support for critical cloud infrastructure and agentic AI pipelines. Participate in on-call rotations, troubleshoot production outages, manage incidents, and lead root-cause analyses. Use LLM agents to scan logs, correlate traces, generate incident post-mortems, and deploy chaos-testing agents to probe infrastructure and fix vulnerabilities. Required Skill Set: Strong observability experience for multi-agent systems using LangChain, LangGraph, and LangSmith. Deep integration with Galileo and LangSmith for tracking prompts, token costs, latency, and evaluations (RAG accuracy, hallucination rates, agent safety). Expertise with Loki (logs), Grafana (dashboards), Tempo (traces), and Mimir/Prometheus (metrics). Srikala Elpula Talent Acquisition Srikala.elpula@xoriant.com
More at Xoriant