Staff Mobile Engineer · Flutter GDE · Deep learning since 2018
Shipping on-device AI (LiteRT) to 4M+ users at KBTG.
15 years in mobile
iOS · Android · Flutter
Staff @ KBTG · 4M+ users
LiteRT shipped to 4M+ users
Real-time face liveness
On-device, privacy-preserving
I've been a mobile engineer for 15 years. I began studying deep learning in 2018 (Deep Learning Specialization, Stanford/Coursera) — well before the on-device AI wave. That preparation is now shipping in production: LiteRT face liveness on 4M+ users at KBTG, where I serve as Head of the Mobile Guild (60+ engineers) and lead a team of ~10 mobile engineers in a 3,000-person tech organization.
My work sits where mobile and AI meet — not as a job pivot, but as a deliberate, multi-year alignment. I lead by setting architectural standards (Flutter-Native hybrid strategy, security, observability) while staying hands-on with the code that proves them. Three principles guide that work:
This is the work I've been quietly preparing for. If it intersects with what you're building, I'm always up for a conversation.
For a high-security financial app, we needed real-time face liveness running entirely on-device — no biometric data leaving the phone, no server-call latency. Since 2022, I've led the integration and ongoing optimization of LiteRT face liveness: architecting iOS/Android bridges via platform channels, tuning inference across device variance, and coordinating across data science, mobile, and security teams.
Result: production on-device AI processing sensitive biometric data locally, holding real-time detection accuracy across millions of daily authentications.
A financial app serving millions needed enterprise-grade performance under strict transaction security and volatile network conditions across diverse devices. I architected a high-performance optimistic-loading architecture — executing flows instantly while resilient fallback callbacks catch transactional anomalies and securely enforce safety policies (logging the user out on critical mismatches). I also directed the optimization of biometric security loops by eliminating redundant platform-channel context handshakes.
Result: the fastest biometric login speed in the financial industry, with a flawless compliance record and zero security breaches.
Scaling mobile architecture standards for 60+ engineers within a 3,000-person tech organization, while keeping a financial super-app stable for a massive user base. As Head of the Mobile Guild, I define the Flutter-Native Hybrid Strategy and core technical standards, act as the primary technical authority on complex architectural decisions, and own the CI/CD and observability infrastructure (Firebase, Analytics) that lets the org move fast safely.
Result: standardized coding practices, reduced technical debt, and a "Zero Downtime" strategy that absorbed major platform shifts (e.g., Privacy Manifests) without service interruption.
Where the next wave of on-device intelligence is heading.
On-device LLMs for cross-platform Flutter apps — Gemini Nano, MediaPipe LLM Inference, and lightweight open models. Personalized assistants without server dependencies, with privacy preserved on the device. Exploring quantization, prompt engineering for small models, and integration paths.
Flutter & Flash: AI Mascot on the Edge — talk ↗AI-driven UI generation in Flutter. Streaming widgets from agents instead of rendering static screens. A new paradigm for adaptive interfaces.
A2UI: GenUI with Flutter — talk ↗Pushing LiteRT performance further — quantization-aware training, hardware-accelerated inference (Metal / NNAPI), and model-size reduction for production constraints.
On-Device AI with LiteRT — talk ↗
Exploring on-device AI as a complement to cloud AI. While powerful models live in the cloud, many personal and responsive features benefit from running directly on the device — this talk covers practical implementation using TensorFlow Lite (LiteRT).
TALK
Feb 18, 2026
Exploring Agent-to-UI (A2UI) architectures using dynamic Generative UI (GenUI) in Flutter. AI agents that stream, construct, and render customized UI widgets in real-time.
View Slides → Watch on YouTube →
TALK
Nov 23, 2025
On-device AI using Gemini Nano to create an AI-powered mascot on edge devices. Flutter integration with on-device AI for personalized experiences without server dependencies.
View Slides →
TALK
Jul 26, 2025
Why choose between native and Flutter when you can use both? Flutter's Add-to-App feature for seamlessly integrating Flutter modules into existing iOS and Android projects.
View Slides →Mar 24, 2026
In 2023, when Gemini was first released, we were amazed AI could answer questions we couldn't even find on Google. By 2026, we've grown tired of just reading.
Read on Medium →Dec 3, 2025
Have you ever looked at your app's mascot, that friendly face guiding your users, and thought, "wouldn't it be amazing if it could… change?"
Read on Medium →Dec 15, 2023
Continuing my previous article on Face Liveness Detection in Flutter — enhancing performance with a native approach instead of Flutter workarounds for image transfer.
Read on Medium →Founded and lead Flutter Mekong — a regional community of 300 developers across Southeast Asia, sharing architectural patterns, security practices, and on-device AI strategies derived from production work.
📚 View All My Articles on MediumOpen to interesting conversations about mobile, on-device AI, and where they meet.