Research Scientist, Robotic Dexterous Manipulation (PhD) at Meta

Redmond, Washington, United States -

Full Time

Start Date

Immediate

Expiry Date

26 Jan, 26

Salary

0.0

Posted On

28 Oct, 25

Experience

2 year(s) or above

Remote Job

Yes

Telecommute

Yes

Sponsor Visa

Skills

Robotics, Dexterous Manipulation, Control Theory, Optimization Algorithms, Machine Learning, Computer Vision, Embedded Systems, ROS, Deep Learning, Tactile Sensing, Multimodal Perception, Collision Avoidance, Research Development, Prototyping, Cross-Functional Communication, Scientific Software

Industry

Software Development

Description

The Sensor and Systems Research group at Reality Labs Research is seeking a Robotics Research Scientist to drive foundational and applied research aimed at advancing state-of-the-art robotic architectures, dynamic in-hand manipulation, generalizable dexterous and functional manipulation, as well as tactile and multimodal sensing and perception. In this position, you will collaborate closely with a multidisciplinary team of researchers and engineers to push the boundaries of robotics science and technology. Responsibilities Explore forward-looking ways and novel robotic architectures to advance dynamic in-hand manipulation, generalizable dexterous and functional manipulation (rigid to deformable objects in-hand to against the environment) Research novel sensors, robotic systems architectures, planning and control algorithms that involve tactile and multimodal vision and perception, dexterous manipulation and collision avoidance Develop machine learning models and end-to-end applications for robotics, dexterous manipulation, and contextual understanding Invent novel paradigms for robotics sensing and intelligence, leveraging a variety of sensing and machine perception modalities (images, video, audio, tactile, etc.) Develop efficient models deployable to robotic systems, integrate research into full system-level robotic prototypes Qualifications Currently has, or is in the process of obtaining a Bachelor's degree in Computer Science, Computer Engineering, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta Currently has or is in the process of obtaining a PhD degree in Robotics, Artificial Intelligence, Computer Vision, Physical AI, Machine Learning, relevant technical field, or equivalent practical experience. Degree must be completed prior to joining Meta Research experience in at least one of the following research areas: robotics, dexterous manipulation, control theory, optimization algorithms, representation learning, self-supervised learning, multimodal learning, vision-language-action (VLA) models, reinforcement learning, imitation learning, robotics policy development, computer vision, egocentric perception, embodied AI and/or LLMs Experience in C/C++ and Python and deep learning frameworks (e.g., PyTorch, TensorFlow) Must obtain work authorization in country of employment at the time of hire, and maintain ongoing work authorization during employment Proven track record of achieving significant results as demonstrated by grants, fellowships, patents, as well as first-authored publications at leading workshops or conferences such as Robotics (RSS, ICRA, IROS, CoRL, T-RO, IJRR), Machine Learning (NeurIPS, ICML, ICLR, AAAI, JMLR), and Computer Vision (CVPR, ICCV, ECCV, TPAMI) Experience with research and development of humanoid robots Experience with embedded systems and communication protocols Experience with robotics frameworks such as Robot Operation System (ROS), along with experience working with robotic simulations and real-world robots Experience bringing-up and debugging prototype/scientific software-hardware systems (e.g., robotics platforms, multi-camera sensing/tracking solutions, wearable sensing systems) Experience working and communicating cross-functionally in a team environment

Responsibilities

The role involves exploring novel robotic architectures and advancing dynamic in-hand manipulation. You will also develop machine learning models and integrate research into full system-level robotic prototypes.