Summary
Cheng-hsin Emily is a research engineer specializing in computer vision and machine learning with eight years of experience building real-time perception systems and applied research at Meta's Pittsburgh FRL. She has hands-on expertise in 3D multi-object tracking (patent filed), neural rendering, object detection, and video recognition, with an ICCV publication and industrial deployments from LiDAR-based trackers to mobile-optimized YOLO models. Emily bridges academia and industry—having contributed to projects at Carnegie Mellon, Princeton, Harvard, and Zoox—where she implemented core detection pipelines and novel temporal LSTM 3D MOT systems from scratch. Her work spans both algorithmic innovation and engineering pragmatism: model compression, implementation in PyTorch/PyTorch3D, and production-focused C/C++ systems for AR and robotics. Based in Pittsburgh, she combines strong research credentials (MS in Computer Vision from CMU) with product-minded delivery across startups and large labs. An understated strength is her cross-cultural, multidisciplinary background—from building EV prototypes to leading course programs—which helps her translate cutting-edge vision research into deployable systems.
8 years of coding experience
2 years of employment as a software developer
Field Of StudyEntrepreneurship/Entrepreneurial Studies, Field Of StudyEntrepreneurship/Entrepreneurial Studies at IESE Business School
Academic Exchange, Guanghua School of Management, Academic Exchange, Guanghua School of Management at Peking University
Master of Science - MS, Computer Vision, Master of Science - MS, Computer Vision at Carnegie Mellon University
Hong Kong University of Science and Technology (HKUST)
Academic Exchange, Computer Science, Academic Exchange, Computer Science at ETH Zürich
traditional chinese, English, Chinese, German, Mandarin