ML Applied Research Scientist
Developing state-of-the-art multimodal search for the next generation of AI.
Building search and video understanding systems for large-scale AI. Previously, I spent my PhD teaching robots to navigate the world using a camera, publishing at top-tier conferences along the way.
Expertise
Multimodal AI Model Training and Finetuning Long Video Understanding Information Retrieval Large-scale Benchmarking Image-based Localization
Selected Publications
See all on Google Scholar 
BMVC 2022
Global Proxy-based Hard Mining for Visual Place Recognition
Amar Ali-Bey, Brahim Chaib-draa, Philippe Giguere