About this role
The Operations Engineer (Principal Engineer — Tools & Platforms) will provide expert technical leadership across the infrastructure tooling ecosystem, focusing on observability, automation, IaC, ITSM platforms, and AI-augmented operations. The role is responsible for building and governing engineering platforms that enable Cloud, Network, Security, Database, and Voice towers to operate at scale. A primary focus is embedding AI-augmented capabilities, such as LLM-driven runbook automation, agentic ITSM workflows, and intelligent alert correlation, to reduce operational toil. Responsibilities include designing observability platforms, engineering IaC (Terraform/Pulumi), managing CI/CD and GitOps pipelines, and owning ITSM platform engineering. The candidate will engineer LLM-powered runbook automation, build multi-agent orchestration workflows (LangChain, LlamaIndex, CrewAI), and design RAG architectures for knowledge bases. Requirements include a minimum of 12 years of experience in platform, tools, or infrastructure engineering, with at least 7.5 years specifically in Agentic Orchestration. A 15-year full-time education is mandatory. Preferred qualifications include experience with Crossplane, eBPF-based observability, and AI/ML infrastructure management. The position is based in Gurugram.