Senior Network Automation & Agentic AI Developer

Kyndryl India; Bengaluru; On-site; INR 4,500,000 - 6,000,000; Full time

Job summary

Kyndryl India is looking for a Senior Network Automation & Agentic AI Developer to lead autonomous AI agents for diagnosing infra faults and safely applying changes across a global, multi-vendor network environment.

You will bridge enterprise networking with Generative AI, architect MCP-enabled tools, and implement event-driven remediation while ensuring rigorous safety and HITL controls. The role demands advanced Ansible, Python, and multi-vendor exposure.

Qualifications

• 10+ years in Enterprise Network Engineering, DevOps, or Systems Automation.
• 3+ years building infrastructure automation or developer toolchains.
• Hands-on development with LLM APIs (OpenAI, Claude, Ollama) is a plus.

Responsibilities

• Architect scalable Ansible playbooks and custom modules for multi-vendor environments.
• Build Python middleware to interface with Cisco, Meraki, Versa, and Zscaler APIs/SDKs.
• Design autonomous AI Agent workflows for network troubleshooting and RCA.
• Develop MCP clients/servers to expose internal tools to LLMs as executable tools.
• Create event-driven remediation using EDA, Celery, Redis, or Kafka.
• Ensure HITL gates and strict input validation to secure production changes.

Skills

Automation & Programming

AI & GenAI Ecosystems

Enterprise Networking & Security

Vendor Stack Experience

DevOps & Observability

Tools

AWX/Tower

GitHub Actions

GitLab CI

Job description

Role Overview

We are seeking a visionary and hands-on Senior Network Automation & Agentic AI Developer to pioneer the next generation of intent-based, self-healing network infrastructures. In this role, you will bridge the gap between traditional enterprise networking and cutting-edge Artificial Intelligence. You will not just write scripts; you will architect autonomous AI Agents capable of diagnosing infrastructure faults, correlating real-time telemetry, and safely executing deterministic changes across a global multi-vendor environment.

Key Responsibilities

• Advanced Ansible Engineering: Architect scalable, production-grade network configuration playbooks, custom roles, and execution environments using Ansible Automation Platform / AWX. Develop custom Python plugins/modules to extend Ansible functionality where native vendor support is limited.
• Multi-Vendor API Integration: Write highly concurrent Python middleware to interface natively with the REST APIs and SDKs of our core infrastructure stack (Cisco Nexus/ACI, Meraki Dashboard, Versa Director, and Zscaler).
• AI Agent Orchestration: Design, develop, and deploy autonomous multi-agent workflows using Generative AI frameworks (e.g., LangGraph, CrewAI, LangChain) to automate complex network troubleshooting, validation, and root-cause analysis (RCA).
• Model Context Protocol (MCP): Build and maintain custom MCP clients and servers to securely expose internal networking tools, documentation (RAG), and script suites as executable "tools" for LLMs.
• Event-Driven Remediation: Build closed-loop automation systems using Event-Driven Ansible (EDA) or asynchronous message queues (Celery/Redis/Kafka) to ingest real-time syslogs and trigger proactive self-healing workflows.
• Guardrails & Safety Architecture: Implement strict software boundaries and input validation schemas (e.g., Pydantic) ensuring LLM-generated variables are deterministically parsed, with mandatory Human-in-the-Loop (HITL) approval gates before configuration changes impact production.

Required Technical Skill Set

• Automation & Programming: Advanced Ansible AAP, Python (Object-Oriented, Asyncio, FastAPI), robust try/except exception handling, Ansible Core, AWX/Tower, and Jinja2 templating.
• AI & GenAI Ecosystems: Deep practical experience with LangGraph, LangChain, or CrewAI; strict JSON/Function Calling; Model Context Protocol (MCP); Semantic Routing; and vector databases (Milvus, Chroma) for network RAG pipelines.
• Enterprise Networking & Security: Solid understanding of L2/L3 routing (BGP, OSPF, VXLAN EVPN), SD-WAN architectures, and Secure Service Edge (SSE) frameworks.
• Target Vendor Stack (Highly Desirable): Hands-on API experience with Cisco IOS-XE/NX-OS, Meraki SDK, Versa Analytics, and pyZscaler.
• DevOps & Observability: Git/GitOps workflows, CI/CD pipelines (GitHub Actions/GitLab CI), and log streaming architectures (ELK Stack, Kafka, or Splunk).

Experience & Qualifications

• Total Experience: 10+ years in Enterprise Network Engineering, DevOps, or Systems Automation.
• Automation Focus: 3+ years of dedicated experience building infrastructure automation or developer toolchains.
• AI Exposure: 1+ years of hands-on application development involving LLM APIs (OpenAI, Anthropic Claude, or local Ollama engines).