Research Engineer, Multimodal Reinforcement Learning
职位介绍
Design and implement scalable multimodal reinforcement learning algorithms for multi-turn reasoning in text + vision environments.
Scale training environments using an ecosystem of autoraters and autousers to enable semi-verifiable learning at scale.
Advance retrieval-augmented reasoning to bridge single-turn and multi-turn embeddings and improve grounding in visuals.
Plan, run, and analyze complex RL experiments with rigorous scientific methodology and reproducibility.
Collaborate across teams to align research with product needs in Search, Lens, and YouTube and drive shared pipelines.
Contribute to cutting-edge models, publish results, and influence next-generation AI capabilities while upholding safety and ethics.
Scale training environments using an ecosystem of autoraters and autousers to enable semi-verifiable learning at scale.
Advance retrieval-augmented reasoning to bridge single-turn and multi-turn embeddings and improve grounding in visuals.
Plan, run, and analyze complex RL experiments with rigorous scientific methodology and reproducibility.
Collaborate across teams to align research with product needs in Search, Lens, and YouTube and drive shared pipelines.
Contribute to cutting-edge models, publish results, and influence next-generation AI capabilities while upholding safety and ethics.
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。
已有账户？ 登录
相似职位
其他可能适合您的职位。