Penny TestFlight beta
A money coach you can just ask. Link your bank once, then ask about your spending in plain words, by typing or by voice, and get the answer back as a sentence and a chart.
AI answers that render while they're still being written. Payments that go through with no signal. Clinical AI that never sends a patient's voice off the phone. I've been shipping iOS since 2011 across banking, retail, payments, health and smart cities. Below are the decisions behind that code, not just the job titles.
Each card opens the full story: the constraints, the options I turned down, the design I chose, and what I'd change today.
I built the real-time LLM streaming layer and the chat surface for a generative-AI investing assistant inside a flagship iOS app: eight Swift/SwiftUI modules, from the entry point to the tokenizer.
I led the 0→1 SwiftUI checkout hub, built around an offline transaction queue that syncs when the device reconnects.
Apple Foundation Models fine-tuned with LoRA for clinical vocabulary, plus live two-party transcription in video consults. Built solo across iOS, Android and the backend.
I designed the core Swift package for networking, OAuth, SSL pinning and shared UI, and shipped the Smart City app's first App Store release.
I wrote the build, sign and deploy pipelines for four grocery banner apps, and shipped the Gamification module to the full customer base behind feature flags.
Toolbox. Swift 6 and 5.x, Objective-C, SwiftUI, UIKit, Combine, async/await, actors, Sendable, Core Data, Core Animation, Core Graphics, App Intents, WidgetKit, TipKit · MVVM-C, Clean/VIP, protocol-oriented design, SPM modularization · Apple Foundation Models, Core ML, LoRA, LLM streaming · URLSession, Alamofire, GraphQL (Apollo), OAuth 2.0, Keychain, SSL pinning · XCTest, Swift Testing, XCUITest, Instruments · Fastlane, GitHub Actions, Xcode Cloud, Crashlytics, Sentry · React Native, Node.js/TypeScript.
Education. B.E., Computer Technology, Priyadarshini College of Engineering, R.T.M. Nagpur University, 2011.
Solo and end to end: the client, the backend and the release. These are where I test ideas before I'd recommend them to a team.
A money coach you can just ask. Link your bank once, then ask about your spending in plain words, by typing or by voice, and get the answer back as a sentence and a chart.
A WhatsApp sales agent for car dealerships. It answers inventory questions around the clock through an OpenAI tool-calling agent and hands serious buyers to a human. It ships as a signed, notarized desktop app so dealers can install it themselves.
On-device AI for doctor–patient consultations: live two-party transcription and note summaries from a LoRA-tuned Apple Foundation Model. Patient audio stays on the phone.
The beta runs on Penny's test server with a test bank. No real bank account is needed, and none should be used.
user_goodPasswordpass_goodCode, if asked1234Full details are in the MeetPenny app privacy policy. Penny explains your own spending. It isn't financial, tax or legal advice, and it's for people 18 and older.
Four habits that show up in every case study above. Each one links to where it actually happened.
I co-designed the streaming schema with backend and AI-platform teams before writing a parser, and gave a ~20-app framework explicit interface contracts and a versioning strategy.
No signal at a customer site. A response type the app has never seen. A stream arriving faster than the UI can draw. Those cases set the architecture, not the happy path.
A core package under ~20 apps, a payments package that ended rewrites in 3, and a coach-mark framework other engineers adopted. Leverage beats heroics.
Six worth your time. The rest, including older reference forks, is on GitHub.
Native SwiftUI client for OpenAI's chat API with streaming. Published January 2023, soon after the API launched.
On-device image generation with Stable Diffusion on iOS, published shortly after the model's release.
The shared Swift package behind the clinical AI client: domain logic, transport and AI orchestration types.
Penny's agent: answers questions over six months of transactions by calling analytics tools rather than doing arithmetic in the model.
CarSales Bot: Baileys transport, agent loop and SQLite inventory behind a three-tier service layout.
Data structures and algorithms in Swift, kept as a public interview-prep reference.
All 44 public repositories are on github.com/imuks.
I'm looking for senior and lead iOS roles on product teams doing serious work with Swift, on-device ML or AI on iOS. I'm based in Toronto and London, Ontario, and I'm a Canadian citizen. I can relocate immediately to San Francisco, New York or Seattle, and I'm TN-eligible for US roles, with no lottery or petition needed.