稳定性AgenticOps工程师 - TikTok研发
Core
Build and maintain observability and stability infrastructure for TikTok's global C-end business, including user growth, social, live streaming, and e-commerce, using AI agents to enhance incident response, root cause analysis, and change management.
Role type
Senior IC SRE/AgenticOps Engineer
Builds
Multi-region disaster recovery observability chains, intelligent diagnostic agents, change management platforms, and stability tooling for global user-facing products.
Domain
Internet / Distributed Systems / AI Engineering
Deliverable
production ML models
Required skills
Distributed systems architecture, Observability (AppLog/Monitorlog), Incident management, Root cause analysis, Change management, LLM/Agent engineering, Tool/Skill orchestration, Context management, Evaluation frameworks, System design
Preferred skills
C/C++/Go/Python/Java/PHP, Large-scale system stability (SRE), Release automation, Human-AI collaboration
Technologies
AppLog, Monitorlog, LLM, Agents, Dry-run systems, Trace systems
Responsibilities
Design multi-region disaster recovery capabilities for observability chains; Build intelligent diagnostic agents for alarm discovery and root cause localization; Develop change management products including impact analysis and quality inspection using large models; Create reusable skills and unified context for stability platform agents.
Seniority
Senior, hands-on IC