Emerald is an MIT spin-off founded by CSAIL faculty and researchers to fundamentally change the way health is monitored in the home. Based in Cambridge, we are looking for motivated technical talent to join our small but high-powered team as we take Emerald to the next level.
A few positions are listed below, but we are always looking for talented individuals.
If that's you, email us at: email@example.com
At Emerald, we are building a full-fledged distributed system consisting of reliable, high performance IoT sensors that collect and process wireless signals, and a cloud infrastructure that securely receives and stores all the data. The cloud also performs advanced AI and machine learning techniques to build accurate and detailed health analytics. As a core team member, the ideal candidate would be multi-talented, excited to tackle hard problems, and deliver at startup pace while working with a small, tight knit group of skilled and experienced engineers.
Qualifications: Ph.D., or Masters' with 2 years work experience. A versatile software engineer who has designed and built challenging systems. Experience in security, cloud, and embedded systems is a plus.
COMPUTER VISION/APPLIED MACHINE LEARNING RESEARCHER
Emerald develops novel neural network models that interpret radio signals to extract human pose, as well as a variety of physiological metrics - breathing, heart rate, sleep quality, sleep apnea etc. We believe that deep learning can revolutionize our ability to understand and interpret wireless signals, similar to the dramatic advances it has brought to computer vision and NLP. Such capabilities will not only transform healthcare, but would augment our intrinsic human senses of sight and sound, allowing us to use wireless signals to “see” through walls and occlusions.
Example academic papers related to Emerald:
Through-Wall Human Pose Estimation Using Radio Signals
M. Zhao, T. Li, M. Alsheikh, Y. Tian, H. Zhao, A. Torralba and D. Katabi
Computer Vision and Pattern Recognition (CVPR), 2018, Spotlight presentation
[PDF] [Website] [Video]
Learning Sleep Stages from Radio Signals: A Conditional Adversarial Architecture
M. Zhao, S. Yue, D. Katabi, T. Jaakkola and M. Bianchi
International Conference on Machine Learning (ICML), 2017
[PDF] [Website] [Video] [Slides] [Talk] [Science Highlight]
Qualifications: Ph.D with expertise in deep learning techniques, as demonstrated by a publication record in top conferences such as ICML, CVPR, and NeurIPS. Experience in solving computer vision problems such as pose estimation, detection, segmentation, and scene analysis preferred.