RetailNext is the worldwide market leader and expert in brick-and-mortar retail analytics. We track more than a billion shopping trips per year by collecting data from nearly 100,000 sensors in retail stores and analyze trillions of data points annually. Headquartered in San Jose, CA, RetailNext is a growing global brand operating in more than 40 countries. Cutting-edge Computer Vision is at the core of the RetailNext's suite of proprietary technologies. Our R&D team works on problems ranging from multiple object tracking and facial analysis, to image registration, mosaicking, and 3D reconstruction. We recently branched out from our roots as a software company by designing and building our own cloud-managed stereo sensor, Aurora, that features onboard shopper detection and tracking analytics using video, in addition to WiFi and Bluetooth-based analytics and on-board HD video recording.
The need to understand shopper behavior drives us to do novel research in object, action, and gesture recognition, and we are looking for a Computer Vision Research Scientist to join our R&D team to help with those efforts. You will have an enormous opportunity to conduct applied research and development in Computer Vision and Machine Learning, that will become part of real-time applications analyzing visual data across hundreds of thousands of sensors worldwide. In particular, you will be involved in exploring and developing CV/ML techniques to perform object detection; including parts based modeling and inference, and training and using SVM/LSVM classifiers, convolutional neural networks and deep networks as detectors. These techniques will be applied towards solving real world problems like human, upper body, head, and face detection, facial landmark detection, recognition, and pose estimation in challenging “in-the-wild” environments. Your research will create intellectual properties, leading to patents and/or publications in international conferences and peer-reviewed journals.
The position requires a Ph.D. in Computer Vision or Machine Learning. The position also requires a proven research track record of peer-reviewed journal/conference publications in top-tier venues. Strong programming skills in C/C++, MATLAB and rapid prototyping experience is required.
Develop state-of-the-art computer vision algorithms for object detection, classification, and recognition
Prototype hardware and software solutions for detection, classification, and recognition
Develop computer vision techniques for object detection: devising discriminative features, parts based modeling, SVM/LSVM classifiers or CNN based detection; and for facial analysis: face detection, landmark detection, recognition, classification, and pose estimation
Contribute research applicable to RetailNext product development
Develop robust software for integrating multiple sensors and tracking systems