Sheridan College CS • Cloud Computing Specialization

Software Developer &
Creative Systems Builder

Hi, I'm Chen. I build physical computing installations, retro game engines, and playful interactive software. Grounded in my research on AI reasoning and specification compilers, I turn autonomous systems into tangible human experiences.

GitHub LinkedIn Email

Toronto, ON

Featured Project & Hardware Installation

🏆 Winner: Best Hardware Project — BearHacks 2026Physical Computing • Edge AI • Human-Robot Interaction

EchoBin — Autonomous Sassy Waste-Sorting Installation

Physical Edge Hardware Intervening at the Point of Disposal via Behavioral Nudges

Improper waste sorting is one of the easiest environmental problems to solve, yet municipal guidelines remain widely confusing. EchoBin is an autonomous physical computing installation built to intervene directly before mistakes happen. By pairing real-time computer vision with conversational speech synthesis, it inspects items on approach and uses humor and playful friction to actively educate users.

EchoBin Exterior View with Ultrasonic Sensor Eyes and Camera

EXTERIOR SENSOR FACEHC-SR04 proximity sensor mounted as "eyes" beneath wide-angle USB camera

EchoBin Internal Chassis showing Raspberry Pi, GPIO Wiring, and Cable Management

CHASSIS & INTERNAL HARNESSService door opened: Raspberry Pi 4, GPIO breadboard wiring harness, and stepper drive

💡 The Design "Why": Friction Over Signage

Most sustainability campaigns rely on static informational posters that people ignore during routine disposal. For international students and newcomers, navigating distinct municipal streams (landfill vs. organics vs. co-mingled recycling) creates decision fatigue.

We designed EchoBin to introduce physical and conversational friction. By locking the lid and verbally calling out mistakes with a sassy persona, the bin forces conscious re-evaluation. Humor was chosen deliberately: it disarms defensiveness and makes environmental correction an entertaining social moment rather than a sterile reprimand.

⚡ The Engineering "Process": Pipeline Concurrency

Migrating from laptop mockups to a headless Raspberry Pi introduced severe interaction latency. Our initial prototype processed steps synchronously in a linear blocking waterfall:

Audio Listen → Vision Inference → Text Generation → Audio Playback (>4s lag)

This delay destroyed the conversational rhythm. We resolved this by refactoring into a multi-threaded, queue-based architecture. Audio listening, Gemma vision classification, and ElevenLabs speech generation run concurrently in non-blocking worker threads, maintaining conversational continuity and state retention across multi-turn user arguments.

Raspberry Pi 4Gemma Vision MultimodalElevenLabs Voice AIAsynchronous Worker Queue

Read Full Project on Devpost →

More Featured Projects

Bachelor's CS ThesisAI Alignment

Sequential Dual-LoRA vs. Monolithic Distillation

Addressing reasoning unfaithfulness where LLMs cheat their own visible logic. Uses runtime adapter hot-swapping on Qwen-3-8B to physically decouple thinking from answering.

Scientific Contribution:Proves that wiping the KV-cache between stages forces the model's output to condition strictly on explicit reasoning tokens.

PyTorchvLLMQLoRA

Read Thesis →

Game Engine & Compiler Pipeline16-Color EGA Strategy

三國志外傳 — Spec-Driven Retro Game Synthesis

A creative-technical hybrid compiling a 3-layer declarative specification (`layout`, `elements`, `states`) into prompt constraints to eliminate vision-model hallucinations in retro game generation.

Engine Features:Renders a 41-province polygon canvas map, a 10×10 tactical battlefield hex grid, and an 8-state transition machine in an authentic 640×400 EGA color palette.

YAML SpecHTML5 CanvasState Machine

Case Study & Demo →

Work Experience

C# Developer

EQ Consulting Inc • Toronto, ON

Feb 2022 – Dec 2023

Engineered comprehensive financial models in C# and C++ for Equity, FX, and Commodity products, delivering pricing and risk analytics.
Developed user interfaces for traders using Excel and VSTO, facilitating access to quantitative models and decision making.
Innovated Risk and Profit & Loss (P&L) visualization tools providing actionable data analysis for trading strategies.
Automated portfolio data aggregation processes through scripts, reducing manual data handling.

Information Services Technical Support Lead

North York General Hospital • Toronto, ON

2020 – 2021

Developed internal web tools using Angular, Node.js, and MySQL to track and manage shift slots for hospital staff.
Led technical support at vaccination centers, overseeing hardware/software configuration and proactively resolving issues.
Authored Python scripts to automate administrative processes, saving operational time and ensuring data accuracy.

Financial Engineer Analyst

Scotiabank • Toronto, ON

Apr 2019 – Sep 2019

Implemented financial modeling calculations into core C/C++ libraries and proprietary programs in consultation with market traders.
Developed interface layers between end-user products and core models connecting C++ with VBA in Excel.
Wrote data sanitation and repair scripts in Python and Bash to optimize batch jobs.

Technical Skills

Languages

JavaPythonC#C/C++VBABashSQL

AI / ML & Systems Frameworks

PyTorchUnsloth (QLoRA)vLLMRaspberry PiOpenCVGame Engines & CanvasElevenLabs API

Web & Databases

AstroHTML5 CanvasNode.jsAngularMySQLMongoDBSQL Server

Cloud & Platforms

AWS (Solutions Architect)Cloudflare PagesGitLinux EnvironmentVisual Studio

Education & Certifications

Education

Expected Graduation 2026

Honours Bachelor of Computer Science

Sheridan College • Oakville, ON

Specialization: Cloud Computing

Certifications & Honors

WIN

Best Hardware Project — BearHacks 2026

Awarded for EchoBin Robotic Waste Installation

AWS

AWS Certified Solutions Architect – Associate

Issued 2025

MDB

MongoDB Certified Professional Developer Associate

Issued 2021

Software Developer & Creative Systems Builder