LLM AIOps Development Engineer - Data Center Networking

What you'll do

• Develop streaming telemetry pipelines and a real-time network observability platform for physical and virtual networks.
• Build machine-learning diagnostics and root-cause analysis, plus LLM/Agent tools for troubleshooting and controlled remediation.
• Forecast network capacity and risk, and engineer a reliable, scalable platform from data collection through online inference and automated actions.

What they ask for

• Deep understanding of data-center network architectures, EVPN/VXLAN, BGP/OSPF, and the Linux network stack.
• Mastery of Golang or Python, with strong coding and system-design skills.
• Familiarity with microservices, Docker/Kubernetes, and CI/CD.
• Interest in LLM and Agent technologies, with insights or hands-on experience applying them to operations, such as RAG, tool use, or safety evaluation.

Nice to have

• Experience with big-data pipelines or observability technologies such as Kafka, Flink, ClickHouse/TSDB, Prometheus/OpenTelemetry, or Neo4j.
• Experience with hyperscale networks, LLM/Agent operations projects, open source, high-performance networking, or network configuration and control systems.

Tools

Golang, Python, Docker, Kubernetes, Kafka, Flink, ClickHouse/TSDB, Prometheus/OpenTelemetry

AI focus

Apply machine learning and deep learning for network anomaly detection, correlation, noise reduction, root-cause analysis, and capacity/risk prediction; build RAG-based operations assistance and Agents for controlled remediation and runbook execution.