光子 AI-大模型质量工程师-游戏方向
Core
Design and execute quality assurance strategies for large language models (LLMs) in gaming, covering RL+agent workflows, inference performance, and model effectiveness.
Role type
Senior LLM Quality Engineer (Gaming)
Builds
Production-ready LLM services and gaming features
Domain
Gaming + Large Language Models
Deliverable
production ML models
Required skills
LLM testing, RL+agent validation, inference performance testing, root cause analysis, test automation, protocol compatibility testing, model effect evaluation
Preferred skills
AI-driven test efficiency optimization, monitoring solution design, data visualization
Technologies
RL, agent frameworks, inference engines, performance testing tools
Responsibilities
Define test scope and quality metrics based on business requirements; design test cases for normal, exception, boundary, and high-concurrency scenarios; execute specialized tests for RL+agent flows and model performance; identify root causes of model anomalies and coordinate fixes; build monitoring and data analysis tools; apply AI capabilities to optimize the testing lifecycle.