混元强化训练框架研发工程师（深圳/北京/上海）
Core
Develop and maintain an Agent framework for research scenarios, supporting reinforcement learning, data generation, and automated evaluation.
Role type
Senior IC machine-learning engineer (Agent framework)
Builds
Research-grade Agent frameworks and evaluation pipelines
Domain
Artificial Intelligence / Large Language Models
Deliverable
production ML models
Required skills
Python, asynchronous programming, Kubernetes, containerization, large model training workflows, AI programming tools
Preferred skills
Reinforcement learning, data generation, automated evaluation, system optimization
Technologies
Python, Asyncio, Kubernetes, AI programming tools
Responsibilities
Develop and maintain Agent frameworks for research scenarios; Optimize framework usability, stability, and performance; Integrate external Agent strategies and evaluation logic; Collaborate with algorithm teams on engineering large model training paradigms.
