I build AI systems
that ship.

MS CS at Northeastern. Swift Student Challenge 2026 winner. I work on multi-agent systems, on-device inference, vision pipelines, and full-stack products, thirteen of them written up in full.

View work GitHub
Apple Swift Student Challenge 2026 winner, sole developer
Northeastern University Graduate TA: Computer Vision, Generative AI, HCI
IEEE AISP 2024 Published researcher
PMI San Francisco 3x award winner

Selected work

All projects →

ANU

Apple Swift Student Challenge 2026 winner

A voice-first iOS assistant whose brain runs on the phone: Gemma 4 E4B through LiteRT, on-device classifiers routing every message, and the cloud only as a sanitized, optional fallback.

  • swift 6
  • litert
  • gemma 4 e4b
  • swiftui
Case study
86.7% task classifier, 60-case eval
300+ unit and UI tests green in CI
92.6% routing accuracy
85.3% of queries routed at zero API cost

Dual-LLM Personalization System

Final project for Northeastern’s graduate Generative AI course, written up as a NeurIPS-format paper

A three-layer router that classifies query complexity and dispatches each request to the right model, cutting cascade rate from 30.8% to 14.7%.

  • python
  • scikit-learn
  • gpt-4o
  • streamlit
Case study

Notova

Three native platforms, zero audio server-side

Privacy-first voice notes: iOS and macOS share one Swift core, Android is a parallel Kotlin app on the same contract, and the backend is scoped so tightly it has no code path to receive audio at all.

  • swift 6
  • kotlin
  • typescript
  • oauth2
Case study
3 native platforms, one pipeline contract
0 bytes of audio the server sees
3 front-ends over one engine
$0 running cost

Meeting Bot

No bot joins the call, and the audio never leaves the Mac

Captures whatever audio is already playing on macOS, transcribes it locally with Whisper, and ships a native app, a CLI and a Chrome extension over one engine.

  • python
  • whisper
  • swiftui
  • chrome extension
Case study
Work
Case studies and builds across agents, vision, and full-stack
About
Experience, education, and the stack I work in
Contact
Email, LinkedIn, and resume