AI Agent Engineer (Stability) - TikTok
Core
Building Stability AgenticOps as a productivity infrastructure for TikTok's stability domain, focusing on observability, incident recall, and intelligent diagnosis to enable unattended operations and closed-loop fault resolution.
Role type
Senior IC AI Agent Engineer (Stability/SRE)
Builds
Stability operating system, observability Agents, change-hosting products, and horizontal capability building for Stability AgenticOps
Domain
Internet / Distributed Systems / SRE / AI Agents
Deliverable
production ML models
Required skills
Backend programming (C/C++/Go/Python/Java/PHP), distributed systems fundamentals, observability pipeline design, incident localization, system architecture design, LLM/Agent engineering (tool invocation, context assembly, evaluation)
Preferred skills
Large-scale distributed systems experience, SRE/observability/release systems experience, LLM/Agent engineering practice
Technologies
AppLog, Monitorlog, CLI, Agent, large models
Responsibilities
Build multi-region disaster recovery for core observability pipelines; develop Agent-based intelligent diagnosis for alert detection and root-cause localization; design technical architecture for change-hosting products and support managed daily releases; build unified context, task planning, and controlled execution capabilities for Stability AgenticOps