Computer Vision and Machine Learning Engineer
Palo Alto, CA
Location/City : CA - Palo Alto
Area Code : 650
Job Type : 1: Full Time
Id : 23255
#23255 Computer Vision and Machine Learning Engineer
Location: Palo Alto, CA
Every day, two million passengers and their baggage are screened at US airports. Millions more are screened at international airports, office buildings, infrastructure centers, and more. Beyond people, billions of pieces of cargo, mail, and freight are scanned. What most of these have in common is little automation and very manual process. We are tapping into these unexplored datasets to develop solutions that increase security and efficiency.
We are seeking an engineer with a background in applied deep learning and/or more traditional computer vision techniques to work alongside our CTO in developing object recognition algorithms on 2D and 3D data, and working independently to experiment on new datasets or with new techniques.
We're seeking someone passionate and driven to learn, as the scope of the work may change over time to encompass higher dimensions of data and different sensors.
- Working with 2D and 3D datasets from various sensors (x-ray, CT, LIDAR, etc.) to develop generative and discriminative models.
- Training and deploying machine learning models for object detection, tracking, and recognition.
- Adapting deep learning methods with traditional computer vision methods to build robust, configurable systems.
- At least three years of hands-on experience with applied computer vision and machine learning algorithms, in a research or company environment.
- Publications or significant projects undertaken in machine learning
- Programming experience Comfortable with large projects in Python or C++, and excellent software engineering skills. Good habits around testing, documentation, and writing robust and maintainable code..
- Solid mathematics background (linear algebra, 3D geometry, probability, optimization)
- Expert knowledge in deep learning architectures for computer vision, and associated libraries & frameworks (Tensorflow, PyTorch, Caffe)
- Hands-on experience with image processing, graphics (3D and 2D), and CV libraries (OpenCV, OpenGL, dlib, etc.)
- Comfortable with reading and implementing new research papers
- Open source contributions
- Previous work analyzing 3-dimensional data, including segmentation, reconstruction, classification, or manipulation
- Strong communication skills, including experience writing white papers and proposals for government funding.