Computer Vision / Robotics Research Scientist
Bostondynamicsaiinstitute in Cambridge, MA
Our Mission
Our mission is to solve the most important and fundamental challenges in AI and Robotics to enable future generations of intelligent machines that will help us all live better lives. Research Scientists will have proven hands-on experience developing and realizing state of the art computer vision systems for robot environment understanding with a focus on object-centric representations.
EEO Statement We provide equal employment opportunities to all employees and applicants for employment and prohibit discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.
- Research new computer vision algorithms for robotic manipulation and develop interfaces between robot perception and skill execution. This may include designing object representations, grounding skill parameterizations, building environmental state estimators and developing other related algorithms
- Develop and implement these computer vision algorithms and integrate them with robotic systems .
- Work with fellow researchers and engineers to develop prototypes, test component systems, and field vision algorithms on robotic platforms.
- Collaborate on publications to be submitted at worldwide conferences
- PhD in a robotics-relevant field with Computer Vision / Machine Learning Focus
- 5+ years of experience in research and development (concurrent with PhD)
- Good grasp of a broad set of techniques related to computer vision and machine learning
- Strong development skills with Python
- Experience with ROS
- Experience with fielding research level computer vision systems on physical hardware. Robotics setting preferred
- Experience with object representation learning, 3D object modeling, scene graph estimation, object pose estimation, skill transfer, predicate learning, Gaussian splatting, point tracking, or correspondence learning
- Experience with ROS 2 and robotic software integration (Strongly recommended).
- Experience with deep learning frameworks such as PyTorch
- Advanced programming skills in Python or C++
- Proven track record in top-tier conferences and journals in Computer Vision, Machine Learning, Robotics, and related fields