I build product on top of models and own whether it holds up once real people are using it. At Meta I shipped an LLM classification product from zero to 310,000+ accounts actioned at 94% human-validated precision, built the eval harness behind it, and red-teamed Meta AI before its Threads launch. Before that I launched Community Notes on Threads from zero across iOS, Android, and Web. Five years and 20+ launches at Meta, working end to end in Python from model integration through offline evaluation to client rollout.
Experience
Meta
New York, NY · 2021 – Present- Shipped an LLM classification product from zero, a pluggable, protocol-based Python system deciding roughly 10,000 cases a day. Owned the eval harness against human-labeled data, the prompt and model iteration loop, and the serving path. Median time from report to action fell from days to under an hour.
- Turned it into shared platform infrastructure. Partner teams onboard onto one eval and decision pipeline in weeks instead of months.
- Probed Meta AI for adversarial prompts, jailbreaks, and misuse before its Threads launch, then defined and shipped the safety controls that followed.
- Built Community Notes on Threads from zero across iOS, Android, and Web, including contributor onboarding, the note-writing and rating flows, and the consensus surface readers see. Grew daily contributors 97 to 1,790 and 14-day retention 18.4% to 31.7%, the highest among peer apps.
- Launched About This Profile on Threads to 132M users and established the app's first reusable cross-platform components, and scaled Instagram's About This Account from 11M to 80M eligible users.
- Led engineering for Threads-only accounts, shipping standalone creation, login, recovery, and settings on iOS and Android against a hard EU deadline, plus the integrity controls that unblocked the public Threads launch.
- Led engineering for election transparency on Instagram across backend, mobile, and web for the Philippines, Brazil, and US midterms, covering accounts responsible for 8 billion civic content views.
- Own roadmap and prioritization across 4 platform teams plus policy, legal, and operations partners, and mentor 3 engineers.
Earlier Experience
Coinbase · SWE Intern, Coinbase Prime: Institutional trading features in Go/React making investment-vehicle setup 10× faster; FIDO2 authentication.
2021Amazon · SWE Intern, AWS: Aurora Serverless auto-scaling and a DNS library spanning 100K+ database clusters.
2020Apple · SWE Intern, Core Siri: Microservices parallelizing Siri workflows, improving testing times 300%.
2019Shopify · SWE Intern, Payments: Split-payments to 70K+ merchants on Shopify POS.
2018Skills
- AI & Evaluation
- LLM classifiers, prompt engineering, red-teaming, offline evaluation against human-labeled data, precision/recall tradeoffs, human-in-the-loop and rater systems
- Engineering
- Python, Hack/PHP, Go, Swift, Kotlin, JavaScript, SQL, GraphQL, React, distributed data pipelines, iOS, Android
- Domain
- Trust & safety, content moderation, adversarial abuse, impersonation and identity verification, election integrity
Education
University of Waterloo
Class of 2021Bachelor of Computer Science (Co-op)