DESCRIPTION

Recently acquired byAmazon Robotics, Canvas Technology is using spatial AI to provide end-to-end autonomous delivery of goods. By using state-of-the-art cameras and other sensors, the system perceives its surroundings with unrivaled vision and fidelity. The system combines a mix of high-performance sensors with simultaneous localization and mapping software that builds and continuously updates maps in real-time, completely automatically. It has the capability to ‘see’ and identify different objects, people, vehicles, and places as it moves and react to moving people and vehicles in an intelligent way.

Work with a world-class team and help develop one of the most advanced 3D computer vision systems in the world. You will work on our state-of-the-art real-time perception system utilizing passive image sensors to localize, map, and navigate in complicated dynamic environments continuously over periods of months and years. The systems and algorithms that you develop will be deployed in challenging real-world scenarios adding value to our customers.

You'll be a key contributor to our top-tier computer vision team, have a huge impact in a developing sector and see your research come to life building indoor and outdoor autonomous vehicles.

BASIC QUALIFICATIONS

· Proven passion and experience in computer vision.
· M.S. or PhD in Engineering, Sciences, Mathematics or similar fields.
· Strong mathematics skills.
· Consistent track record of managing high performing development teams that have delivered and deployed complex software systems
· Excellent C++ programming skills including debugging, performance analysis, and test design.

PREFERRED QUALIFICATIONS

· GPU programming experience (CUDA/OpenCL).
· Experience in computer vision.
· Familiarity with mathematical optimization in the context of computer vision.
· Experience using sensors such as cameras, LIDAR, radar, sonar, GPS, IMU, etc.
· Familiarity with SLAM, 3D reconstruction, and calibration.
· Experience with image-space algorithms such as segmentation, optical flow, scene flow, and image decomposition.
· Publications in robotics and computer vision conferences and journals.
· Familiarity with recent machine learning tools and algorithms applied to computer vision problems.
#canvas #canvastech #canvastechnology