Robotic Vision Research Scientist

新加坡全职智能制造 / 工业互联网 / 工业自动化 - 研发

职位描述

Summary of role: This role focuses on developing advanced 3D vision and visual foundation models for robotics, enabling robots to perceive, understand, and interact with complex real-world environments. The researcher will work across areas such as 3D vision, scene understanding, real-to-sim, multimodal perception, and vision-language models, translating cutting-edge computer vision research into robust capabilities for physical robot systems. What you'll be doing:

• Conduct research and development in computer vision for robotic systems, including perception, 3D vision, real-to-sim, scene understanding, object detection and tracking, pose estimation, segmentation, or vision-language models.
• Develop robust visual perception capabilities that enable robots to understand, interact with, and operate in real-world environments.
• Work closely with robotics, control, embodied AI, and hardware teams to translate research ideas into deployable robot capabilities.
• Design experiments, analyse model performance, and improve robustness across different environments, objects, and task conditions.
• Stay current with advances in computer vision, embodied AI, and robotics; contribute to technical direction and research roadmaps.
• Publish research findings in leading conferences and journals where relevant, and contribute to patents or open-source projects where appropriate.

职位要求

What we're looking for:

• PhD in Computer Science, Robotics, Artificial Intelligence, Electrical Engineering, or a related field.
• Strong research track record, demonstrated through high-quality 1st author publications at leading conferences or journals, such as CVPR, ICCV, ECCV, NeurIPS, ICLR, ICML, RSS, CoRL, etc.
• Strong foundations in computer vision and deep learning, with expertise in one or more areas such as 3D vision, visual perception, generative models, vision-language-action models, or multimodal learning.
• Proficiency in Python and deep learning frameworks such as PyTorch, TensorFlow, or JAX.
• Ability to independently formulate research problems, design experiments, and communicate findings clearly.
• Strong problem-solving ability and willingness to work across research and engineering teams. Preferred qualifications:
• Hands-on experience applying computer vision algorithms to real robots, such as manipulation, mobile robots, humanoids, autonomous systems, or industrial automation.
• Experience working with real-world sensor data, including RGB/RGB-D cameras, stereo cameras, LiDAR, tactile sensors, or multi-modal sensor systems.
• Experience with robotic calibration, visual servoing, grasping, manipulation, or sim-to-real deployment.
• Contributions to open-source computer vision or robotics projects.

投递