Video Fit AI
Workout tracking via on-device video analysis and Gemini video APIs.
- Built: Swift iOS camera pipeline + Vapor backend
- Stack: iOS AVFoundation, Gemini, Vapor
- Outcome: end-to-end prototype + architecture writeup
Projects
Selected work across robotics, vision, and iOS. Proof-forward, detail-rich, and iterated in public.
Focus areas
- Robotics
- Autonomy
- Computer Vision
- iOS Systems
- Embedded Controls
Current build
Expressive robotic lamp with Jetson inference, STM32 control loops, and a behavior state machine for responsive motion.
Collaboration
Open to early-stage prototypes, field tests, and systems design partnerships that need quick iteration and clear proof points.
How I build
Each project focuses on tangible outcomes: system architecture, measurable performance, and a documented path to the next iteration.
System-first planning
Define interfaces and constraints early so software, hardware, and controls stay aligned through integration.
Prototype → proof
Ship working demos quickly, then pressure-test assumptions with real data, metrics, and usability feedback.
Documented iteration
Capture architecture decisions, experiment results, and next steps so progress stays visible and repeatable.
Expressive Robotics Lamp
Jetson-powered lamp with personality-driven motion behaviors. PALA: Programmable Autonomous Lamp Assisstant.
- Built: embedded control + motion state machine
- Stack: Jetson, STM32, ROS tooling
- Outcome: early demo with responsive gestures
Pose Estimation Pipeline
Fast pose inference for real-time feedback on mobile.
- Built: optimized inference + data capture tooling
- Stack: Core ML, Python tooling, iOS
- Outcome: on-device prototype targeting real-time performance