As a member of the Autopilot Vision team you will research, design, implement, optimize and deploy models and algorithms that advance the state of the art in autonomous driving. A strong candidate will ideally possess at least one strong expertise in the following areas, and at least a basic familiarity in others: visual odometry, structure from motion, multi-sensor fusion, camera calibration, tracking, object detection/classification, deep learning (convolutional neural networks).
- Develop state-of-the-art algorithms in vision-based localization and mapping
- Optimize code to run efficiently on an embedded device
- Ground truth, test, and validate algorithms for statistical performance, as it relates to current state-of-the art and other sensor modalities.
- Integrate embedded code with the larger Tesla Autopilot development team to introduce new features and capabilities to Tesla’s vehicles.
- Solid understanding of linear algebra, multi-view geometry, numerical optimization
- Excellent C/C++ coding, strong engineering practices, debugging/profiling skills, familiarity with multi-threaded programming
- Experience with sensors related to autonomous driving research such as camera, IMU/GPS, Lidar
- Experience with CUDA/OpenCL, OpenGL a plus
- Experience with state estimation methods a plus
- Ph.D. in computer vision or Machine learning
- Or M.S. with greater than 3 years’ experience in a core computer vision area