Ran Bi is an Applied Scientist with a decade of experience turning complex data into actionable decisions across tech and academia, currently driving ML and analytics work at Amazon from Bellevue. He blends hands-on expertise in SQL, Python, R, SAP HANA and ETL with practical BI delivery—building predictive models, dashboards and optimization algorithms that informed supply-chain and revenue planning at Cisco. Ran’s GitHub contributions show applied ML work on audio-driven talking-face generation, highlighting strengths in model evaluation, visualization and engineering fixes that improve reproducibility. Comfortable communicating across research, product and operations teams, he pairs a researcher’s rigor with product-minded pragmatism to operationalize models. Colleagues rely on him for clear reporting and for bridging statistical insight with scalable data engineering.
Code for "Audio-driven Talking Face Video Generation with Learning-based Personalized Head Pose"
Role in this project:
ML Engineer
Contributions:18 commits, 11 pushes, 34 comments in 9 months
Contributions summary:Ran primarily contributed to the project by modifying scripts related to audio-driven talking face video generation. Their work included fixing issues related to directory handling and missing packages. They also updated scripts for testing, including personalized video generation using poses from a video, and made changes to the visualizer, indicating a focus on model evaluation and visualization. Furthermore, the user updated scripts related to background blending.
Code for Line Drawings for Face Portraits from Photos using Global and Local Structure based GANs (TPAMI)
Contributions:4 commits, 1 push, 5 comments in 1 year
deep-learningcomputer-visiongangansdrawings
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.