Purpose

The position focuses on research and development of computer vision and machine learning algorithms toward analysis, segmentation, recognition, reconstruction, and interpretation of scenes captured by multi-modal data streams including video cameras and range sensors.

Responsibilities

1. Research and development of computer vision, machine learning, and optimization algorithms for feature selection, semantic segmentation, odometry, motion analysis, and recognition/tracking/forecasting of objects and persons
2. Design, development, and integration of the software systems and architectures necessary to realize research prototypes
3. Develop and evaluate metrics to verify reliability of the proposed algorithms
4. Participate in data collection, sensor calibration, and data processing
5. Participate in ideation, creation, and evaluation of related technologies in various domains including scene/traffic objects and indoor robotics
6. Contribute to a portfolio of vision bots, academic publications, and prototypes to demonstrate research value

Requirements

1. Experience in open-source Deep Learning frameworks such as TensorFlow, Pytorch, CNTK, or Caffe
2. Hands-on experience in handling multi-modal sensor data
3. Strong familiarity with machine learning techniques pertaining to visual recognition and/or video analytics
4. Highly proficient in software engineering using C++ and Python
5. Strong written and oral communication skills including development and delivery of presentations, proposals, and technical documents
6. Strong publication record in one or more of the following areas: computer vision, machine learning