LLM AIOps Development Engineer - Data Center Networking

ByteDance
Seattle
Workplace: OnsiteFull timeFunction: Product ManagementSkills: ["Collaboration","System design","Engineering best practices","Proactive problem-solving"]

Build closed-loop AIOps for hyperscale data center networking by creating a real-time observability platform and applying ML/LLM techniques for anomaly detection, correlation, and root-cause analysis. Develop LLM-powered operations assistants (RAG chat) and agent-driven remediation/runbooks, plus capacity and risk prediction to enable proactive scaling and preventative maintenance. Work with NetOps, SRE, and platform teams to deliver a highly available, scalable pipeline from telemetry collection to online inference and autonomous actions.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
ByteDance
ByteDance
1 month ago

LLM AIOps Development Engineer - Data Center Networking

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 31 days agoStatus: Live
Reposted: similar role first listed 1 month ago

Job Summary

Build closed-loop AIOps for hyperscale data center networking by creating a real-time observability platform and applying ML/LLM techniques for anomaly detection, correlation, and root-cause analysis. Develop LLM-powered operations assistants (RAG chat) and agent-driven remediation/runbooks, plus capacity and risk prediction to enable proactive scaling and preventative maintenance. Work with NetOps, SRE, and platform teams to deliver a highly available, scalable pipeline from telemetry collection to online inference and autonomous actions.
Location: Seattle
Workplace: Onsite
Employment Type: Full time
Job Function: Product Management

Key Responsibilities

  • •Collaborate with NetOps, SRE, and platform engineering to deliver AIOps for a large data center network.
  • •Build a streaming network observability platform using multi-source telemetry (gNMI, Netconf, IPFIX/NetFlow, SNMP) for real-time AIOps input.
  • •Develop ML-based diagnostics and root-cause analysis for anomaly detection, correlation analysis, and noise reduction across the network stack.
  • •Create LLM-powered operations assistants (RAG chatbot) and agent-driven remediation/runbooks that can recommend or execute changes safely.
  • •Implement capacity and risk prediction to forecast bottlenecks, high-risk links, and sub-healthy devices, and ensure a highly available, scalable platform.

Key Requirements

  • •Deep understanding of data center network architectures (e.g., Spine-Leaf Fabric) and protocols such as EVPN/VXLAN and BGP/OSPF, plus strong Linux networking knowledge.
  • •Proficiency in Golang or Python with strong coding and system design skills.
  • •Experience building real-time data pipelines/analytics (e.g., Kafka, Flink, ClickHouse/TSDB).
  • •Experience with observability technologies such as Prometheus/OpenTelemetry and building alert/event platforms (including graph databases like Neo4j).
  • •Hands-on interest in AIOps/ML/LLM and agent technologies for operations, such as RAG, tool use, and safety evaluation.
Experience:Hyperscale data centersAIOpsMLLLMReal-time data pipelines
Skills:CollaborationSystem designEngineering best practicesProactive problem-solving
Tech Stack:GolangPythonLinuxEVPNVXLANBGPOSPFMicroservicesDockerKubernetesCI/CDKafkaFlinkClickHouseTSDBPrometheusOpenTelemetryNeo4jGNMINetconf

Company Brief

ByteDance
Develops consumer internet and content platforms, including TikTok and other apps for short-form video, news, and entertainment. It also builds advertising, commerce, and creator tools that connect audiences, brands, and publishers across global markets.
Industry: Digital Media
Company Size: Enterprise (1,001+ employees)
Revenue: USD 1B+
Growth: Established Company
Headquarters: Beijing, China
Founded: 2012
WebsiteLinkedIn