AI Agent 平台研发工程师

- Build evaluation task scheduling - Design LLM gateway for model routing - Develop AI agent evaluation platform core features - Develop DAG based evaluation pipeline UI - Develop agent sandbox execution environment - Execute agent tools - Implement pipeline orchestration engine - Implement token metering - Integrate MCP services - Integrate multi vendor model providers - Manage evaluation datasets - Monitor evaluation task execution - Optimize platform stability and performance - Orchestrate containers for sandbox execution