AIOps Network Engineer: LLM-Driven Observability

TikTok Inc.; San Jose (CA); On-site; USD 162,000 - 388,000; Full time

Job summary

TikTok Inc. is seeking a passionate development engineer for the Network Observation team to build autonomous, AI-powered data center networks. You will craft a panoramic observability platform that ingests streaming telemetry and enables real-time insights across physical and virtual networks.

You will develop intelligent diagnostics and enable LLM-based agents for autonomous remediation, while forecasting capacity and risk to support proactive scaling in a hyperscale environment.

Qualifications

• Solid fundamentals in computer science and networking with data center architectures.
• Proficiency in Golang or Python with experience in microservices, containers, and CI/CD.
• Experience with big data processing and observability tools such as Prometheus/OpenTelemetry.

Responsibilities

• Build a panoramic network observability platform with streaming telemetry from multiple sources.
• Develop an intelligent diagnostics and root cause analysis system using ML/DL for network faults.
• Explore intelligent LLM-based apps and agents for autonomous operations and automated remediation.
• Establish capacity and risk prediction capabilities for proactive maintenance.
• Forge a scalable AIOps engineering system ensuring reliability from data collection to online inference.

Skills

Networking fundamentals

Golang or Python

Docker/Kubernetes

CI/CD

Big data processing

Observability tools

Prometheus/OpenTelemetry

LLM/Agent concepts

Tools

Kafka

Flink

ClickHouse/TSDB

Neo4j

gNMI

Netconf

SONiC

DPDK/eBPF

Prometheus

OpenTelemetry

Job description

TikTok Inc. is seeking a passionate development engineer for the Network Observation team to build autonomous, AI-powered data center networks. You will craft a panoramic observability platform that ingests streaming telemetry and enables real-time insights across physical and virtual networks.

You will develop intelligent diagnostics and enable LLM-based agents for autonomous remediation, while forecasting capacity and risk to support proactive scaling in a hyperscale environment.