Building the future of preventive health. AI-powered health and fitness optimization. Not tracking for tracking's sake, but systems that improve real-world health markers and restore agency over wellness decisions.
Most health tracking is theater. Apps collect data but don't change behavior. Wearables log metrics that users ignore. The gap between measurement and meaningful action keeps widening.
I wanted to build something different—a system where AI doesn't just analyze your meals or labs, but actually helps you make better decisions. Not tracking for tracking's sake, but tools that improve real-world health markers.
Computer vision trained on 100K+ meals. Custom models that understand regional cuisines and portion estimation—not generic food recognition.
Systems Architecture & Data Flow
The hardest part wasn't the computer vision—it was building a pipeline that works on mobile devices with spotty connectivity. We compressed models, implemented progressive enhancement, and built offline-first sync. Results: 90%+ accuracy on meal analysis, sub-2s inference time.
100K+ meals analyzed • $500K ARR
Scaling consumer health tech isn't about features—it's about building trust with your data. Users need to see real results, not just dashboards.
I'm drawn to hard problems at the intersection of emerging technology and human behaviour especially in spaces that are ripe for disruption powered through innovation.