MatthewWang
Student at the University of Waterloo. Incoming Software Engineering Intern at Scispot, working on self-healing for AI agents, January to April 2027.
Available for Summer 2027 internships
Hotfix, a playable arcade cabinet
A black upright arcade cabinet with an orange neon marquee that reads Matthew Wang. Its screen runs Hotfix, a maze game: clear every bit from the maze while three bugs chase you, and grab a patch to fix the bugs for points. Insert a coin to play. Steer with the arrow keys, by pointing with the mouse, or by swiping. P pauses, and Escape leaves the game.
Work
Braid
In development · Lead
A shared memory so that when several people each run their own AI agent, those agents can see what the others have already decided.
- Append-only facts, never edited in place, so the audit trail is free.
- Cheap graph and vector filters run first; an LLM only sees pairs that might actually collide.
- Access control lives in Postgres row-level security, not just application code.
TypeScript · Node.js · MCP · PostgreSQL + pgvector · Docker
SPYDRWEB
Hackathon · 2 people
A five-layer fraud pipeline where an LLM decides which detectors to run, then a person always makes the call.
- A planner chooses which layers to run and how to weight them; routine cases never touch a model.
- Every layer reads the same append-only event log.
- The model recommends, with evidence. It does not freeze an account.
Python · FastAPI · React · Vite · WebSockets · NetworkX
PROJECT: SENTINEL
UTRA Hacks 2026 · team of 5
Robot telemetry into diagnostics and a 3D replay, built in a weekend. Best Use of MongoDB at UTRA Hacks 2026.
- Ingestion sniffs the shape of incoming data so a hardware change does not silently drop records.
- Diagnostics are computed on demand, not on the write path.
- The LLM coaching layer can fail; the metrics still come back.
Python · Flask · MongoDB · React · Three.js
ZermaltBot
Personal project
A CNN chess engine trained on 5,000+ master games, then improved past that baseline with self-play.
- Supervised pretraining first, then self-play — not AlphaZero from random weights.
- Inference is a FastAPI service on Modal’s GPU cloud.
- No published Elo; the claim is that self-play beat the supervised baseline.
Python · PyTorch · FastAPI · Modal
Hotfix
This site · 2026
The arcade cabinet on this site. A maze game rendered live onto a curved CRT.
- The game is a 120 Hz TypeScript loop. The cabinet is just a view.
- The CRT is a shader on a curved mesh, not a post-process.
- Coins to play; three more are hidden in the page.
TypeScript · three.js · Canvas 2D · Astro
Experience
Jan–Apr 2027
ScispotIncoming
Software Engineering Intern · Toronto
Working on self-healing, ai agents
May–Aug 2026
IPMD
Full Stack Developer Intern
- Contributed to the GPU rendering pipeline.
- Built the internal project management tool.
Apr–Nov 2025
DataAnnotation
AI Trainer
School
University of Waterloo
- René Descartes National Scholarship$25,000 entrance award (2025, 2026).
Honours
- Hackathons
- Best Use of MongoDB, UTRA Hacks 20262026PROJECT: SENTINEL, built in under 24 hours with a team of 5. Write-up
- Mathematics
- 3x AIME qualifierAmerican Invitational Mathematics Examination.
- CMOQR qualifierCanadian Mathematical Olympiad Qualifying Repêchage.
- Euclid 89/100 and COMC 67/80Euclid Mathematics Contest and Canadian Open Mathematics Challenge.
- Swimming
- 8 national age-group records10+ years as a national-level competitive swimmer.
- Provincial championship titles
Resume
A PDF, or the same information on a single page you can print from the browser.