The RoleAs 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.
- Train machine learning and deep learning models on a computing cluster to perform visual recognition tasks, such as segmentation and detection
- Develop state-of-the-art algorithms in one or all of the following areas: deep learning (convolutional neural networks), object detection/classification, tracking, multi-task learning, large-scale distributed training, multi-sensor fusion, etc.
- Optimize deep neural networks and the associated preprocessing/postprocessing code to run efficiently on an embedded device
- Solid understanding of linear algebra, algorithms, machine learning, optimization, numerical methods
- Excellent Python coding, strong engineering practices, debugging/profiling skills, familiarity with multi-threaded programming
- Experience with data science tools including Python scripting, numpy, scipy, matplotlib, scikit-learn, jupyter notebooks, bash scripting, Linux environment
- Experience with at least one main stream deep learning frameworks, including TensorFlow, PyTorch, Caffe(2), MXNet
- Experience with computer vision or robotics libraries (e.g., OpenCV, PCL, ROS)
- Experience with CUDA/OpenCL, OpenGL a plus