Computer Vision Engineer (Shenzhen, Brisbane & Atlanta)
To apply, send resume and, if applicable, a portfolio of your work to
1. Work with both 2D (RGB) and 3D (Depth) raw perception data.
2. Solve vision tasks including but not limited to the following:
- Vision sensor calibration (internal and external)
- Identifying and classifying objects, generating bounding boxes, segmenting objects, and generating object masks
- Measuring object sizes
- Estimating and tracking object poses
- Learning/scanning new objects quickly with surface reconstruction
- Identifying and reading barcodes
- Large-scale automatic data collection
- Efficient and autonomous data labeling
- Vision-based mapping, localization, and navigation
3. Program robots to perform the tasks listed above in various lighting conditions, with heavy occlusion, while robots/cameras are moving at high speeds.
4. The job might involve researching particular topics, reading papers, attending conferences, efficiently implementing algorithms for hardware, testing, debugging, parallelization, sourcing sensors and computing platforms, writing documents/papers, and generating patents.
1. Background in computer vision, computer graphics, image processing, machine learning, or other related fields.
2. Very skilled in C++ and Python (knowledge and daily experience)
3. Solid knowledge of computer vision with experience of turning theories into practical programs.
4. Very skilled with vision libraries: OpenCV, PCL, etc.
5. Very skilled with deep learning frameworks: Tensor Flow, Keras, etc.
6. Skilled with machine learning techniques, especially deep learning, reinforcement learning, and transfer learning.
1. Published author in computer vision or graphics journals and attended conferences such as CVPR, ICCV, SIGGRAPH, etc.
2. Experienced in programming, robotics, or vision algorithm competitions.
3. Strong experience in any of the following areas:
- Image detection and segmentation
- Scene comprehension
- Image captioning
- Video analysis
- Multi-object pose estimation
- RGB-D segmentation
- 3D reconstruction
- Motion tracking
- Large-scale datasets creation
- Multi-cluster GPU training
- Open source project collaboration
- Blogging/writing about computer vision or robotics