Hey, I'm Yusef. I'm in my first year at the University of Toronto, intending Math + CS. I spend a lot of my time building apps and working on AI evaluation.
- ⌚ I built the Apple Watch client for Providence with my team at Hack the North.
- 🧪 My eval lab looks at what agents actually did when tool calls fail or evidence is incomplete.
- 🌱 I'm looking for supervised research and Summer 2027 internships. Email me.
Each card links to my contribution. Green labels indicate merged PRs; the PyTorch PR is still open.
As of September 28, 2026, I have 12 merged upstream PRs across six projects, including Apache Arrow slicing and Agent Lightning timeout-report retries.
- Aesthetics AI — my iOS workout-planning and tracking app. App Store · How it's built
- Tiraz — my privacy-first digital wardrobe app. App Store · How it's built
- CallReclaim — a private missed-call recovery MVP. Sample-data demo · How it's built
The public CallReclaim Agent Desk is a separate synthetic demo with no messaging backend. ShiftProof is also a local prototype using synthetic data.
Languages: Python · TypeScript · JavaScript · Swift · SQL
Apps: React · React Native · Expo · Next.js · SwiftUI · watchOS
Experiments: PyTorch · NumPy · Inspect · pytest
Infrastructure: PostgreSQL · SQLite · Supabase · Docker · GitHub Actions
The eval lab includes a frozen 624-trial local-model study. Invalid-output rates differed between conditions, so I withheld improvement claims and kept the descriptive results and missing-output analysis.
The Tiraz study uses garment annotations, not images. Its three seeded models achieved 58.5–59.0% top-1 against a 52.7% baseline on 962 held-out groups; removing context exposed a large drop in prediction-set coverage.
Methods, results, and limitations · PyTorch local validation supplement
I'm available full-time May–August 2027, and open to supervised research during the school year that fits my coursework. I'm a U.S.–Canadian dual citizen, open to Canada, the U.S., relocation, and remote work. Expected graduation: May 2030.
Typing intro and compact grids inspired by DenverCoder1.