Wenli Looi
I am currently a machine learning engineer at Viaduct.
View my resume.
  • Dota 2 Item Recommender System
    Dota 2 Item Recommender System
    Using recommender systems to predict in-game purchases with high accuracy.
  • Henry Wise Wood Math Club
    Henry Wise Wood Math Club
    Website featuring math/CS presentations and interactive 21 game and L game.
  • Minefield
    Minefield is a multiplayer first-person shooter game inspired by Minecraft. It written in C++ using Direct3D 9 and a custom UDP-based protocol.
  • TrainWhacker
    Exciting HTML5-based game. Guide Nopal by avoiding enemies as she fulfills her dream of migrating from Mexico to the United States!
  • WebGL Water
    WebGL Water
    Interactive web-based water simulation (WebGL) featuring reflection, refraction, Fresnel, and specular lighting.
  • WenLiBot
    Intelligent chatterbot where you can talk with a variety of virtual programmed people. Utilizes basic natural language processing techniques.



StanfordStanford University 2018 – 2020

  • MS Computer Science (Artificial Intelligence & Theoretical Computer Science)

  • Mostly part-time except for one full-time quarter as a research assistant for Prof. Jure Leskovec.

University of CalgaryUniversity of Calgary 2012 – 2017

  • BS Computer Science, BS Chemical Engineering (double degree)

Work Experience

ViaductMachine Learning Engineer, Viaduct (Menlo Park, CA) 2021 – Present

  • Working on large scale ML modeling of automotive data and the design and implementation of efficient, scalable, and reproducible production ML systems.

GoogleSoftware Engineer, Google (Mountain View, CA) 2017 – 2021

  • Worked on an internal data processing framework providing features similar to MapReduce/Hadoop, as well as listening for changes on databases, transforming the data, and writing back to the database in a transactional manner.

GoogleSoftware Engineer Intern, Google (Mountain View, CA) 2016 Summer

  • Interned on the team that I currently work for.

MicrosoftSoftware Engineer Intern, Microsoft (Redmond, WA) 2014/2015 Summer

  • Designed and implemented automatic time zone detection for Windows 10. This feature has since shipped to all users. Inventor on U.S. patent 10,503,124 (Automatic time zone detection in devices).


ACM International Collegiate Programming Contest (ACM-ICPC)

  • project cs231n Convolutional Neural Networks (CS 231N). Project: Quantized GANs for Mobile Image Reconstruction [poster, report]

  • project cs236 Deep Generative Models (CS 236). Project: Caption-to-Image Conditional Generative Modeling [poster, report]

  • project cs229 Machine Learning (CS 229). Project: Analysis of Code Submissions in Programming Contests [poster, report]

  • project cs224w Machine Learning with Graphs (CS 224W). Project: Predicting Traffic Congestion on City Road Networks [poster, report]

  • project cs224n Natural Language Processing (CS 224N). Project: Compressed SQuAD 2.0 Model With BERT [report]

  • Other courses: Convex Optimization (EE 364A), Distributed Systems (CS 244B), Infomation Retrieval and Web Search (CS 276), Optimization and Algorithmic Paradigms (CS 261), Probabilistic Graphical Models (CS 228), Randomized Algorithms (CS 265)