LLM AIOps Development Engineer - Data Center Networking

What you'll do

• Build streaming telemetry pipelines and a real-time network observability platform.
• Develop machine-learning diagnostics, root-cause analysis, and capacity and risk prediction capabilities.
• Build LLM-powered assistants and operational agents for troubleshooting, runbooks, and network remediation.

What they ask for

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

Nice to have

• Experience operating or developing for hyperscale data-center networks (100,000+ servers), or significant contributions to an LLM/Agent-based operations project.
• Open-source contributions or practical experience in areas such as SONiC, P4/PINS, eBPF, Prometheus, OpenTelemetry, RDMA/RoCE, SmartNICs, DPDK, or network configuration and control systems.

Tools

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

AI focus

Applies machine learning and deep learning to network anomaly detection, correlation, noise reduction, root-cause analysis, and prediction; builds RAG-based conversational operations assistance and agents that recommend or execute remediation and runbooks.