DevOps Agent研发工程师-火山引擎
Core
Develop a 7x24 intelligent DevOps/SRE Agent platform that autonomously handles fault detection, investigation, localization, repair, and prevention across the full R&D and operations lifecycle.
Role type
Senior IC Machine Learning Engineer (AIOps/Agent Systems)
Builds
Autonomous diagnostic agents, AI-powered observability assistants, and automated runbook execution systems.
Domain
Cloud-native infrastructure, AIOps, and Large Language Model (LLM) application development.
Deliverable
production ML models
Required skills
Go/Python/Java, Cloud-native and distributed systems, LLM/Agent application development, Prompt engineering, Function Calling/MCP, RAG, Vector search, Knowledge graphs, Observability stack (Metrics/Logs/Traces), Complex system troubleshooting.
Preferred skills
AIOps and anomaly detection, Root cause analysis (RCA), Observability platform development, Multi-Agent system design, Automated fault self-healing, ChatOps/Incident management.
Responsibilities
Design Agent Runtime execution strategies and autonomy levels; Build hypothesis-driven cross-data correlation for automated RCA; Develop natural language query assistants and intelligent alert aggregation; Integrate observability tools with CI/CD pipelines for closed-loop repair.
Seniority
Senior, hands-on IC
