AI测试开发Tech Lead - 经营管理与平台
Core
Building an evaluation system for Agents and AI applications covering model performance, business correctness, stability, security, performance, cost, and user experience, while establishing AI-native R&D testing paradigms.
Role type
Senior IC AI Testing Development Tech Lead
Builds
Automated testing platforms, intelligent capabilities for requirement understanding, test case generation, code inspection, defect localization, and regression verification.
Domain
AI Engineering / Quality Assurance / Infrastructure
Deliverable
production ML models
Required skills
Large language models (LLMs), Agent development, RAG, tool calling, model evaluation, E2E automation testing, test platform engineering, data analysis, business logic abstraction
Preferred skills
AI testing, model evaluation, agent evaluation, R&D efficiency platforms, automated testing system architecture
Technologies
LLMs, Agents, RAG, E2E testing frameworks
Responsibilities
Design and implement evaluation metrics for model effects, business correctness, stability, security, performance, cost, and UX; Build intelligent capabilities for requirement understanding, test case generation, code inspection, and defect localization; Establish an E2E testing loop from generation to execution, diagnosis, repair, and re-run; Define methodologies and best practices for AI quality engineering.
Seniority
Senior, hands-on IC