LLM AIOps Development Engineer - Data Center Networking
Core
Design and implement a closed-loop AIOps platform for hyper-scale data center networking, integrating streaming telemetry, ML-based diagnostics, and LLM-powered autonomous operations agents.
Role type
Senior IC LLM AIOps Development Engineer (Data Center Networking)
Builds
Panoramic network observability platform, intelligent root cause analysis systems, LLM-based operations assistants, and automated remediation agents.
Domain
Data Center Networking / AIOps / Large Language Models
Deliverable
production ML models
Required skills
Data center network architecture (Spine-Leaf, EVPN/VXLAN, BGP/OSPF), Linux network stack, Golang or Python, microservices, containerization (Docker/Kubernetes), streaming data pipelines (Kafka, Flink), observability (Prometheus, OpenTelemetry), graph databases (Neo4j), RAG, LLM agents, tool use, safety evaluation.
Preferred skills
Hyperscale data center operations (100k+ servers), LLM/Agent project leadership, open-source contributions (SONiC, P4, eBPF), high-performance networking (RDMA, SmartNICs, DPDK), network configuration systems (gNMI, Netconf).
Responsibilities
Develop streaming telemetry data pipelines integrating multi-source data (gNMI, Netconf, IPFIX, SNMP); Apply ML/DL algorithms for anomaly detection, correlation, and noise reduction on network metrics; Build conversational chatbots using RAG for troubleshooting; Train agents to invoke network change tools and execute remediation plans; Forecast network capacity bottlenecks and risks; Design and develop highly available, scalable AIOps engineering systems.
Seniority
Senior, hands-on IC
