Agentic Ops

Role Overview

This position focuses on building and supporting agentic operations capabilities for enterprise DevOps workflows. The work centers on orchestration, monitoring, and lifecycle management for AI agents, along with integration into infrastructure and delivery pipelines.

Core Work

• Work with agent frameworks such as LangGraph, CrewAI, or AutoGen to design agent-based solutions.
• Create markdown-based documentation that specifies how agents should handle complex decision logic.
• Help build reusable building blocks for agent lifecycle control, orchestration, observability, and usage metering.
• Track and analyze operational metrics such as token consumption, agent success rate, execution cost, and model drift.
• Implement retrieval-augmented generation (RAG) workflows where needed.
• Set up approval checkpoints for high-risk actions and sensitive operations.
• Support integrations using Python and Go, especially for Kubernetes- and Terraform-related workflows.
• Apply MCP concepts within CI/CD pipelines and monitoring environments.

Screening Focus

Applicants are expected to bring a DevOps/SRE background, practical experience with LLMs, vector databases, and MCP-related systems, plus a solid understanding of telemetry, observability, and the role of agents in the DevOps toolchain.

Additional Information

This role is based in Chennai, Tamil Nadu, India and is a full-time onsite position.