混元Agent强化学习框架工程师（深圳/北京/上海）
Core
Develop and maintain an Agent framework for research scenarios, supporting reinforcement learning, data generation, automated evaluation, and experiment reproducibility.
Role type
Senior IC machine-learning engineer (Agent framework)
Builds
Stable, reusable framework components for model/tool invocation, task execution, and evaluation logic
Domain
Artificial Intelligence / Reinforcement Learning / Large Language Models
Deliverable
production ML models
Required skills
Python (asyncio, concurrency), Kubernetes, containerization, large model application integration, modular software design, performance optimization
Preferred skills
Experience with pre-training, SFT, RLHF, or automated evaluation pipelines
Technologies
Python, Asyncio, Kubernetes, Docker
Responsibilities
Research and maintain Agent framework components; optimize framework stability, performance, and concurrency; collaborate with algorithm teams to engineer new Agent paradigms and training pipelines
Seniority
Senior, hands-on IC
