AI Agentic Ops Site Reliability Engineer

About the company

Xoriant is a digital engineering organization headquartered in Sunnyvale, California, with teams across the USA, Europe, and Asia. The company supports businesses ranging from startups to large enterprises, helping them speed up innovation, shorten product launch cycles, and stay competitive. Its work spans digital product and platform engineering, experience design, data engineering, and IoT, backed by a strong product-engineering culture and reusable delivery accelerators. With 30 years of experience, Xoriant focuses on building lasting client partnerships and delivering complex platforms at scale.

Role overview

The company is looking for an AI Agentic Ops Site Reliability Engineer to support autonomous AI agent operations and production infrastructure. The position is based in Bangalore and is intended for professionals with 7 to 10 years of experience.

What the role involves

• Deploy AI agents that can plan actions, execute commands, and help repair infrastructure issues automatically.
• Provide level-3 production support for important cloud systems and agentic AI pipelines.
• Take part in on-call duty, investigate production incidents, coordinate outages, and drive root-cause analysis.
• Use LLM-based agents to review logs, connect trace data, draft incident post-mortems, and run chaos-testing agents to uncover weak points and address vulnerabilities.

Required experience and tooling

• Hands-on observability experience across multi-agent systems built with LangChain, LangGraph, and LangSmith.
• Strong integration knowledge of Galileo and LangSmith for prompt tracking, token-cost monitoring, latency analysis, and evaluation metrics such as RAG accuracy, hallucination rate, and agent safety.
• Practical expertise with Loki for log analysis, Grafana for dashboards, Tempo for tracing, and Mimir/Prometheus for metrics monitoring.

Eligibility

Any graduate can apply.

Contact

Srikala Elpula
Talent Acquisition
[email protected]