Job Description:

• Position Name: AI Agentic SRE(Site Reliability Engineer)

• Location: Bangalore
• Hybrid: 3 days work from Office
• Minimum Relevant Experience: 6-10 Years

• Key Skills: Observability (LangChain/LangGraph); LangSmith; Galileo; Loki; Grafana; Tempo; Prometheus

About the Role:
Validate system performance; build test pipelines; run parallel test suites in Docker.

Required Skills:
• Solid experience with Observability related to multi agent systems using LangChain/LangGraph and LangSmith.
• Deep integration with Galileo and LangSmith for tracking prompt traces, token costs and system latency.
• Utilizing Galileo and LangSmith to run continuous evaluation on RAG accuracy, hallucination rates and agent safety.




• Expert management of Loki(logs), Grafana(dashboards); Tempo(Traces) and Mimi/Prometheus(Metrices).

We transform. SAP® solutions into Value

Recruiter Name: Srinija Adapa

Recruiter Email ID: [email protected]

NTT DATA Business Solutions is a fast-growing international IT company and one of the world’s leading SAP partners. We are a full service provider delivering everything from business consulting to implementation of SAP solutions, including hosting services and support.

📌 AI Agentic Site Reliability Engineer_Senior Consultant (Bengaluru)
🏢 NTT Data
📍 Bengaluru