Research Scientist, Computer Vision (Learning From Videos)
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 cutting-edge computer vision research focused on video generation, spatio-temporal representations, and world models for embodied robotics.
Develop foundation and multi-modal models that reason over 4D scenes and enable reliable real-world deployment on robotic systems.
Train and evaluate models at scale using large-scale real and synthetic datasets; publish in top conferences.
Collaborate with cross-disciplinary teams, mentor interns, and transfer algorithms to production for long-term autonomy.
Contribute to simulation, differentiable rendering, and perception-prediction-planning pipelines for robotics and autonomous driving.
Demonstrate strong programming in Python and PyTorch, with experience in distributed training on cloud platforms such as AWS.
Develop foundation and multi-modal models that reason over 4D scenes and enable reliable real-world deployment on robotic systems.
Train and evaluate models at scale using large-scale real and synthetic datasets; publish in top conferences.
Collaborate with cross-disciplinary teams, mentor interns, and transfer algorithms to production for long-term autonomy.
Contribute to simulation, differentiable rendering, and perception-prediction-planning pipelines for robotics and autonomous driving.
Demonstrate strong programming in Python and PyTorch, with experience in distributed training on cloud platforms such as AWS.
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。