Network Software Engineer - Observability & AI

Overview

Design and build AI-native Network APIs and MCP servers that make Equinix's network observability and inventory data programmable for AI agents and operators, and lead the technical direction for this work.

What you'll do

• Translate network observability requirements (latency anomaly detection, capacity thresholds, topology drift) into clear API contracts and data models.
• Lead architectural reviews and define reference architectures for exposing network intelligence via MCP servers.
• Design systems that integrate streaming telemetry, SNMP, flow data and topology graphs with inventory and asset repositories as a unified programmable layer.
• Build production-grade Network APIs in Python or Java that consume observability telemetry, asset inventory and topology data.
• Implement MCP servers exposing network capabilities as callable tools and data resources for LLM-powered agents.
• Develop agentic pipelines (e.g. LangGraph or similar) enabling network self-service through natural language and structured tool calls.
• Integrate across observability stacks (Prometheus, OpenTelemetry, Kafka, Grafana Loki) and network asset systems.
• Develop unit, integration and agent-interaction tests, including testing of agentic systems for adversarial prompts, tool misuse and multi-step reasoning failures.
• Define deployment and release guidelines for AI-native network services, including canary strategies for MCP server rollouts.
• Troubleshoot production issues across the AI-native stack and prepare runbooks for agent failure modes and API degradation.
• Collaborate with customers and NOC teams to co-design AI-agent-driven self-service network experiences.
• Evaluate emerging AI and networking technologies and mentor junior engineers.

What you'll need

• 5+ years of software engineering experience with a focus on platform, infrastructure or network software systems.
• Demonstrated experience building APIs that consume observability, telemetry or network data at scale.
• Proficiency in Python and/or Java for backend API and data pipeline development.
• Hands-on experience with AI/LLM application development: prompt engineering, tool calling, RAG pipelines, or agent frameworks (LangChain, LangGraph, AutoGen, or equivalent).
• Familiarity with Model Context Protocol (MCP) as a server implementer or consumer, or demonstrated ability to rapidly adopt structured AI tool interface specifications.
• Experience with observability stacks: OpenTelemetry, Prometheus, Grafana, Kafka, or similar streaming/metrics platforms.
• Bachelor's degree in Computer Science, Computer Engineering, or equivalent practical experience.

Nice to have

• Networking certification or demonstrable understanding of network concepts: BGP, MPLS, VLANs, IP addressing and similar.
• Familiarity with network inventory systems, CMDB/DCIM platforms, or graph-based topology data stores.
• Background in agentic system design: multi-agent orchestration, tool safety guardrails, and structured agent output validation.
• Experience with vector databases (Pinecone, pgvector, Weaviate) for RAG-backed network knowledge retrieval.

Details

• Location: Bangalore Office, India.