LiveOps agent
~20 minfrom 2–3 hTime to complete one LiveOps workflow
I worked on an AI LiveOps agent that cut a workflow from 2–3 hours to about 20 minutes.
Now at Zynga · AdTech
Software engineer building AI tooling and ad tech at Zynga.
Changelog
v6.0May 2025 – Present
Zynga · Toronto, ON
AdTech team: AI tooling and ad projects.
v5.0May 2023 – Jun 2024
Hexagon Manufacturing Intelligence
v4.0Sep 2022 – Apr 2023
McMaster University · Hamilton, ON
v3.0May 2022 – Aug 2022
Exchange Solutions
E-commerce and loyalty platforms: a Shopify app on AWS, plus AR, blockchain and data-visualization work.
v2.0Oct 2021 – 2022
McMaster Artificial Intelligence Society · Hamilton, ON
v1.0Jun 2021 – Sep 2021
InsideDesk
Highlights
Recent work, kept high-level.
LiveOps agent
~20 minfrom 2–3 hTime to complete one LiveOps workflow
I worked on an AI LiveOps agent that cut a workflow from 2–3 hours to about 20 minutes.
Ad-config MCP
I designed and led internal tooling for ad-serving configurations at Zynga: a Model Context Protocol (MCP) server and tools that let AI assistants work with ad-serving configuration.
High-value ads
I designed and led a project that helps games identify high-value ads.
Recently shipped
10 projects, newest first.
A control plane for safely delegating software work to autonomous coding agents.
A harness-agnostic platform for handing software work to coding agents in Cursor, Claude Code or any other harness. The goal, from my spec: maximize architecture-approved, verified engineering output per dollar and per minute of human attention.
Role Solo: spec, design and CLI (in progress)
Books tennis and pickleball courts the moment booking opens, every morning.
My parents had to set a 7:30 a.m. alarm every week to get courts at our local club, so I automated it. Members set weekly schedules in a web app, and a bot books the courts each morning and texts the results.
Role Solo, full-stack (2023 version with help from Douglas Chen)
Mobile meal planner: pick meals, get a grocery list, track calories and protein.
A mobile-first meal planner: choose meals and servings, turn them into a grocery list, and track calories and protein against personal targets. Our team of five built it as a front-end prototype on mock meal data, so the “AI-powered meal prep” step is a UI concept.
Role Team of 5: app shell, Auth0 login, meal-planning flow, deploy
Find a place to study at McMaster: search, filters, ratings, favourites and a map.
A mobile-first prototype for finding study spots on McMaster’s campus: search and filter spots, save favourites, mark places visited, rate them, and see them on a map around you.
Role Solo, front-end
A password manager built in one day for the MEC 2024 programming challenge.
A password manager with Auth0 sign-in, an Express API, and passwords encrypted before they are stored in Firebase. I built it in one day with Willie Pai and Mohammad Mohsin Khan for the MEC 2024 programming challenge.
Role Team: Auth0 login, JWT-secured API, dashboard-to-API wiring
My resume as a REST API: Postman-only, rate-limited, with a joke for anyone who POSTs.
An Express + MongoDB API that serves my resume as JSON, one section at a time or all at once. Inspired by Eric Lake’s API resume.
Role Solo
Android app that matches riders headed the same way so they can share a taxi.
CarpoolX matches riders heading to the same destination so they can share a taxi and split the fare, with an upfront fare estimate and safety checks for riding with strangers. Four of us built it as a React Native Android app on a Flask and Firebase backend.
Role Team of 4: repo lead, most of the Flask backend and auth, core screens
Mix subway sounds, chatter and lo-fi music into your own TTC ride-home ambience.
A small ambient-sound web app inspired by ridethesubway: sliders blend subway ambience, background chatter and lo-fi music over a train illustration by the artist mienar.
Role Co-created with Quinn Ha; built the app and audio controls
Upload a lecture video and get an AI transcript to study from. Built at MacHacks 2.
A study tool for recorded lectures: upload a video, watch it beside an AssemblyAI speech-to-text transcript, and (the plan) drag snippets onto your slides to export as a PDF. In 36 hours our team of four built upload, playback and transcription.
Role Team of 4: AssemblyAI integration, repo setup and write-up
A workout planner that schedules rest days, not just workouts. Built at DeltaHacks 8.
A weekly workout planner that deliberately schedules rest days, designed to use Fitbit sleep and activity data to decide when to train and when to recover. Willie Pai and I built it in 36 hours at DeltaHacks 8.
Role Team of 2: Fitbit API integration, landing page, deploy
Tech specs
B.Eng., Software Engineering (Co-op)
McMaster University, 2020–2025 · Dean's Honour List (2020–2023) · McMaster Honour Award (2020–2023) · Courses: System Design, Data Structures and Algorithms, OOP, Software Design, Databases
One more thing
Software Engineer at Zynga, based in Toronto, Canada.
The Launch edition: the same facts as every other version, in a different shape.
| Intro | Keynote |
|---|---|
| Experience | Changelog |
| Impact | Bento |
| Projects | Release stack |
| Skills | Spec sheet |
| Contact | Keynote CTA |
Chrome palette · Keynote type · Scenes motion
How this site works →