About the job
You will work closely with CVML researchers and engineers to develop world-class perception, spatial input, and 3D tracking algorithms and software. The role focuses on inventing and implementing state of the art CVML algorithms to solve cutting edge problems. As a member of a fast-paced team, you have the unique and rewarding opportunity to shape upcoming products that will delight and inspire millions of people every day.
Responsibilities
Invent and implement state-of-the-art CV/ML algorithms for perception and 3D tracking
Design robust, efficient solutions optimized for mobile and on-device hardware
Collaborate across software, hardware, and systems teams to ensure efficient end-to-end pipelines and effective use of Apple silicon
Iterate quickly based on data, feedback, and system constraints
Contribute to technical direction and roadmaps for next-generation perception and AI capabilities
Translate research ideas into production-quality systems and integrations
Qualifications
Minimum
Bachelor’s degree with 5+ years of relevant industry experience
Strong foundation in computer vision in one or multiple of these areas, including 3D rigid/non-rigid object tracking, multi-view geometry, and visual-inertial odometry (VIO)
Proficiency in Python and deep learning frameworks such as PyTorch
Preferred
PhD in computer vision, machine learning, robotics, or related fields
Experience across both classical 3D computer vision and deep learning
Familiarity with visual-inertial or multi-sensor fusion
Strong C++ and systems engineering skills, with experience delivering robust, efficient algorithms
Self-motivated with a proven record of prioritization and on-time delivery