Key Responsibilities:

• Conduct research on multi-view reasoning/rendering algorithms that can be integrated into multi-agent systems operating in dynamic environments.
• Develop and implement algorithms and methodologies for optimizing model architecture, training processes, and inference procedures.
• Design, development, and integration of software systems necessary to realize research prototypes and test them in both simulation and in real platforms.
• Develop software infrastructure and tools, such as test scenarios, baseline algorithms, module interfaces, etc. to facilitate team's development efforts.
• Contribute to a portfolio of patents, academic publications, and prototypes to demonstrate research value.

Minimum Qualifications:

• Ph.D. (or M.S. w/ 2 years of research) in Computer Science, Robotics, or a related field with a strong focus on 3D computer vision, computer graphics or embodied AI.
• Experience in 3D vision (e.g. neural rendering, multi-view geometry, multi-camera tracking, SLAM, etc).
• Strong programming skills, preferably in Python and experience with deep learning frameworks (e.g., TensorFlow, PyTorch).
• Strong problem-solving skills and the ability to think critically and creatively.
• Excellent communication skills, both written and verbal.
• Ability to work collaboratively in a team-oriented research environment.

Bonus Qualifications:

• Experience with multi-agent systems including information sharing, multi-robot coordination, representation learning, semantic reasoning, etc.
• Familiarity with handling data from sensors and hardware, including cameras, LiDAR, GPS, IMU, etc.

Duration: 3 years