Research Engineer, Reward Models Training
在手机上跟进您的申请 Whileresume 免费应用，支持 iPhone 和 Android。
职位介绍
Lead the end-to-end engineering of reward model training, from data ingestion to deployment and evaluation.
Design scalable, reliable training pipelines capable of supporting larger models and multiple data modalities.
Build robust data pipelines for collecting, processing, and integrating human feedback into reward model training.
Optimize training infrastructure for throughput, efficiency, and fault tolerance across distributed systems.
Collaborate with researchers to translate novel reward modeling techniques into production-ready systems.
Develop tooling and monitoring to ensure training quality and accelerate iteration cycles.
Design scalable, reliable training pipelines capable of supporting larger models and multiple data modalities.
Build robust data pipelines for collecting, processing, and integrating human feedback into reward model training.
Optimize training infrastructure for throughput, efficiency, and fault tolerance across distributed systems.
Collaborate with researchers to translate novel reward modeling techniques into production-ready systems.
Develop tooling and monitoring to ensure training quality and accelerate iteration cycles.
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。