Location: Vancouver, Canada
Remote: Yes (worldwide)
Willing to relocate: Yes
Technologies: iOS, Swift, SwiftUI, UIKit, Swift Concurrency, TCA, Core ML/Vision, HealthKit, watchOS, BLE/NFC, Push Notifications, App Store Review, OWASP MASVS, visionOS
Email: hn@drobinin.com
Résumé: https://drobinin.com/consultingSenior iOS engineer / Apple-platform consultant with 12+ years of experience.
I build and fix iOS and Vision Pro apps from medical devices and high-traffic consumer apps to vibecoded startups. I also help teams get difficult apps approved: App Store rejection triage, reviewer-note/metadata fixes, and fractional senior iOS support for startups.
TF-IDF was the first thing I tried - it works great for stopwords but it doesn't handle cross-language bleed of filler words well, and the short life-event messages ("he died", etc) use common words and get aggressively down-weighted.
I had some asymmetry analysis when looking at directional sentiment and per-person question rates - that's fun indeed!
I also went with the Jaccard convergence and the endearment categories instead of wordclouds, so that I could see how word choices are changing across time.
I also use the Note to Self which is built into Signal and appears just like any other conversation. I use that for temporary stuff like addresses and keep it clean.
CV: https://drobinin.com/consulting
Senior iOS engineer / consultant (12+ years). I build and fix iOS and Vision Pro apps from medical devices and high-traffic consumer apps to vibecoded startups struggling to pass App Store reviews.
The one I went to is indoors, although not a tunnel but a Nissen hut [1].
--