I’m an Applied Scientist at Twitch working on the Proactive Safety team building ML applications to detect and remove harmful content and behavior from the platform.

Previously, I was an Applied Research Scientist at ServiceNow that joined through the acquisition of Element AI. I worked on problems in NLP (question answering, semantic search, natural language understanding) and everything around it (research, engineering, scaling). Some of my highlights at Element AI were building and deploying NLP models for Knowledge Scout to deliver smarter search capabilities on unstructured data, and developing document entity extraction models for Document Intelligence to automate document processing.

I completed my MAsc with Dr. Mark Crowley and Dr. Joon Lee in the Electrical and Computer Engineering department at the University of Waterloo working on data-driven decision making in healthcare. My research focused on developing methods for home health monitoring and data-driven decision-making systems using the abundance of data coming from various devices today.

Before that, I finished my Bachelor’s degree in Computer Engineering at Concordia University in Montreal. During that time, I worked as a research intern at NTT in Japan on media event detection from online videos, and worked on digital signal processing and embedded systems as a research assistant at Concordia University in collaboration with Thales Group. I also completed co-op internships as a software developer in aerospace at CAE and participated in many extra-curricular activities in robotics and electronics competitions.

In my free time, I like playing basketball, hiking, camping and cycling.

News

• Writing: Information extraction from 2D documents: a hybrid approach (March 25, 2020).
• Talk: Advice on becoming a full-stack ML practitioner, McGill University (October 28, 2019).

Personal Projects

	Shogun Machine Learning Toolbox Google Summer of Code, 2017 Summary Applied machine learning algorithms on health data for mortality prediction.
	Lung Cancer Detection Kaggle Data Science Bowl, 2017 Code Built a deep learning model that predicts whether or not a patient will develop lung cancer using CT scan images.
	ConSat-3 Space Concordia Canadian Satellite Design Challenge, 2016 Concordia article / Globe & Mail Developed and integrated embedded Linux software applications for a cube satellite. Our team won 1st place against competing Canadian universities.
	Machine Competition Jeux de Genie, 2015 Video / Live Competition / Article Developed the software for a fully autonomous robot that had to complete multiple tasks around a complex track. The robot won the 1st prize competing against all engineering schools in Quebec.
	LearnStream UofTHacks IV Code Developed an app for students with hearing impairments that transcribes speech from a lecture to text in real time. Our project won the 3rd overall prize.
	EyeTalk Hack4Health 2.0 Event Winners Built a mobile app that synthesizes words and sentences through detection of eye movement, helping users with severe MS and ALS to communicate better. Our team received a 500$ award.

Publications

• Olivier Nguyen, Population-level Indicators of Physical Activity, Sedentary Behaviour and Sleep in Canada based on Twitter, University of Waterloo MASc Thesis (2018).
• Puri Arjun, Ben Kim, Olivier Nguyen, Paul Stolee, James Tung, Joon Lee. User Acceptance of Wrist-Worn Activity Trackers Among Community-Dwelling Older Adults: Mixed Method Study. JMIR mHealth and uHealth 5-11 (2017).
• Olivier Nguyen, Yongqing Sun, Kyoko Sudo, Akira Kojima. Semantic Video Classification by Fusing Multimodal High-Level Features. Meeting on Image Recognition and Understanding (2015).