Research Engineer, Reward Models Platform
在手机上跟进您的申请 Whileresume 免费应用，支持 iPhone 和 Android。
职位介绍
Partner with researchers in the Rewards and Fine-Tuning teams to understand workflows and automate high-friction tasks.
Design and build scalable infrastructure to experiment with reward signals, including rubric editors, data analysis tools, and robustness evaluations.
Develop automated quality checks to detect reward hacks and other pathologies during training.
Create tooling to compare reward methodologies (preference models, rubrics, programmatic rewards) and quantify their impact on model behavior.
Build end-to-end pipelines from dataset preparation to evaluation and deployment, with monitoring and observability to surface issues.
Collaborate with scientists to translate research requirements into platform capabilities, balancing speed, reliability, and maintainability.
Design and build scalable infrastructure to experiment with reward signals, including rubric editors, data analysis tools, and robustness evaluations.
Develop automated quality checks to detect reward hacks and other pathologies during training.
Create tooling to compare reward methodologies (preference models, rubrics, programmatic rewards) and quantify their impact on model behavior.
Build end-to-end pipelines from dataset preparation to evaluation and deployment, with monitoring and observability to surface issues.
Collaborate with scientists to translate research requirements into platform capabilities, balancing speed, reliability, and maintainability.
查看完整职位
工作职责、任职要求、技能与福利 — 免费创建账号即可查看。
或
已有账户？
登录您可能也感兴趣的职位
暂无高度相似的职位 — 以下是最新职位。