I'm an engineer with 10+ years in mobile, now focused on AI systems that deliver value in production, with on-device ML chained into pipelines that run reliably at the edge.
- On-device & local-first ML — inference at the edge across mobile and desktop, with portable artifacts (self-contained model files that run across platforms) and local LLMs for summarization and analysis.
- Cross-platform delivery — shipping ML-backed features into mobile and desktop apps via native binary modules.
Notes I write while studying ML papers and fundamentals:
- ML & inference — PyTorch · ONNX · local LLMs · Apple Foundation Models · Apple Vision (OCR)
- Systems — Rust · Python · API services for near-real-time processing
- Mobile — Swift / SwiftUI (iOS · watchOS) · Jetpack Compose (Android) · React Native
- Targets — iOS · watchOS · macOS · Android · Linux



