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.
  • Exposure Segregation
    Exposure Segregation
    Using cell phone mobility data to develop a measure of exposure segregation, the likelihood of the rich and poor individuals crossing paths.
  • 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 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.

Contact: wenli at looiwenli dot com LinkedIn GitHub


Engineer mainly experienced with large-scale ML/data systems but with a wide range of other interests including on-device ML, Linux kernel, embedded systems, networking, competitive programming, sociology, languages.


StanfordStanford University 2018 – 2020

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

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 production ML/data systems with PySpark, Iceberg, Clickhouse, XGBoost/LightGBM, SHAP, MLflow.

  • Built batch ML prediction framework and feature store with a focus on high performance and fast experimentation, supporting baselines, metrics, reproducibility, explainability, missing/partial features.

  • Modeling of vehicle sensor and fault code data including transformer model using TensorFlow Official Models NLP library.

GoogleSoftware Engineer, Google (Mountain View, CA) 2016 (Intern), 2017 – 2021

  • Worked on an internal C++ large-scale data processing framework similar to MapReduce/Flume, widely used in Google Ads.

  • Designed major portions of a framework to listen to Google F1/Spanner changes and write back transformed data, as well as many other features, performance improvements, and regression testing. Have C++ and Python readability.

  • 20% project: Identifying misinformation in social networks using TensorFlow Graph Neural Networks.

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

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

Personal Projects
  • On-device ML: Real-time AI camera surveillance on very low-end systems (e.g. Intel GPU). Built on top of raw Vulkan/DirectX shaders for unparalleled performance and stability. Generating OpenCL shaders using TensorFlow Lite and converting to HLSL while optimizing and adding 8-bit quantized weights/activations. Contributing some small improvements back to TensorFlow.

  • Linux kernel/OpenWrt: Submitted kernel patches to support Qualcomm QCN5502 WiFi SoC based on reverse engineering. Added support for new Wi-Fi routers in open-source firmware, including reverse engineering proprietary image formats.

  • Competitive programming: ACM ICPC World Finals contestant in 2015 and 2019, and top 500-1000 worldwide in Google Code Jam / Meta Hacker Cup. Gave algorithm lectures and writes contest problems (e.g. on Kattis).

  • Language learning: Learning several languages. Intercepting Duolingo app traffic with Android TLS certificate bypass and mitmproxy to get unlimited hearts and automatically convert the course content to Anki flashcards.

  • Home automation: Fully custom system for lights/outlets, furnace, sensors involving PCB design, IP cameras, microcontroller firmware in C (ESP32/ESP8266, Arduino/AVR, STM8/STM32), data storage/analysis/web UI (Elasticsearch, Go, React).

  • project cs231n Computer Vision (CS 231N): Quantized GANs for Mobile Image Reconstruction [poster, report]

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

  • project cs244b Distributed Systems (CS 244B): Google File System From Scratch [report]

  • project cs224w Graph ML (CS 224W): Predicting Traffic Congestion on City Road Networks [poster, report]

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

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

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