I am a Machine learning engineer with passion in actualizing the value of AI and proven experience in building scalable ML systems.
I am a lifelong student.
I am currently a Machine Learning Engineer at Affirm in San Francisco. I was formerly a Machine Learning Engineer at Nextdoor in San Francisco and at Dessa (acquired by Square) in Toronto.
I am an avid reader. My favourite books include The Brothers Karamazov, The Count of Monte Cristo, East of Eden, Flowers for Algernon, Lolita, One Hundred Years of Solitude.
I enjoy dancing salsa and bachata.
I have a B.Sc from the University of Toronto in Math & Physics.I was a math teaching assistant at UofT since my second year and have collaborated with faculty to develop curriculum for a data science course. I have also mentored participants and judged projects at HackOn(Data) 2017 — a Toronto data science hackathon.
I played guitar, jazz & classical piano.
Extracted, cleaned and pre-processed over 13 million records from remote SQL database. Trained XGboost valuation model on AWS EC2.
A guide on how to set up Spark with Jupyter on AWS EC2 instances with S3 I/O support. Presented at Toronto Apache Spark #19.
A solution for determining the most optimal placement of location-based information maps throughout Toronto.
I use python multiprocessing to preprocess Lung CT Images efficiently on all available CPU cores on AWS compute instances.
An exploration of satellite images using AWS S3 and boto3 for the kaggle DSTL Satellite Imagery Feature Detection challenge.
* As a member of the University of Toronto Data Science Team (UDST).
How machine learning teams can apply Modern Agile and Extreme Programming engineering principles to deliver high-quality, flexible and low cost-of-change ML projects that yield a net reduction in development time and production time.
Technical presentation on state-of-the-art NLP model Google BERT
Practical and theoretical methodologies for applying deep learning to real-world applications, including public health sciences, based on techniques employed in real-world contexts.
MAT245: Mathematical Methods in Data Science: An introduction to the mathematical methods behind scientific techniques developed for extracting information from large data sets.
|3T0 M. & P. and Associates Scholarship||2018|
|Norman Stuart Robertson Scholarship in Mathematics||2017|
|Coexter Scholarship in Mathematics||2017|
|C.L. Burton Scholarships for Mathematics and/or Physical Sciences||2017, 2016|
|Third Place at HackOn(Data)||2016|
|NSERC Undergraduate Student Research Award||2016 (UToronto)
|Dr. James A. & Connie P. Dickson Scholarship in Science and Math||2015|
|University of Toronto Scholar
Joseph Alfred Whealey Incourse Scholarship
|Howard Ferguson Provincial Scholarship||2014
2015*, 2016*, 2017*
A list of useful data science resources.
What I’ve read.
This website template is based off Patrick Steadman’s website. It uses the Lanyon jekyll theme, and is hosted on Github Pages.