Open to NA SWE roles
I build the systems that make AI agents predictable in production.
Most engineering happens in the messy middle: retries that lose money, agents that drift off-script, migrations that touch real users. That's where I build.
5th-year CS + BBA at Waterloo, five engineering roles deep. I've shipped payment infrastructure at Clearco, an AI market-research agent at QuadReal, and data pipelines at Eclipse Automation. On my own time, I wrote a disk-based database engine in Go from scratch. The thread: systems where retries don't lose money and agents don't drift in production. Mostly, I like shipping things people use.
Where I've shipped.
Where I've studied.
Tools I reach for.
Things I've built.
A disk-based DB engine in Go with B+Tree indexes for O(log N) reads, crash recovery via copy-on-write and fsync, and a SQL parser supporting multi-table queries.
Full-stack daily journaling app with Google OAuth, localStorage draft auto-save, and chapter-level API caching; serves 40 active users.
Recent posts.
Start a project with a deliberately minimal harness — interactive USER gates, docs-first, no autonomous loop — and graduate to autonomy only after customer evidence (personas, interviews, simulation reports) appears.
Have the hook config file declare only *what events to subscribe to* and route every one of them to a single handler binary; keep all branching, transformation, and policy in that handler.
A single append-only file where an autonomous harness records every task it could not automate, who handled it manually, and the condition under which automation could resume.
