Embedded AI / Edge Intelligence / Autonomous Systems

I work on AI systems that run beyond the cloud: autonomous vehicles, model compression, wearable-sensor intelligence, and privacy-preserving recommendation.

View Projects Resume GitHub

Jetson Edge AI Runtime for DonkeyCar

Camera-LiDAR robotic control deployment on Jetson Nano, with ONNX/TensorRT FP16 actor inference, runtime profiling, async logging, safety gates, and 20-minute shadow validation. Completed at IntelliSys Lab, Stevens Institute of Technology.

Stack: Python / DonkeyCar / PyTorch / ONNX / TensorRT / Jetson / ROS LiDAR

Case Study / GitHub

FalCom / APPFL Compressor Acceleration

Python/C ABI integration, native C codec work, OpenMP/SIMD CPU optimization, and guarded CUDA q8 experiments for model-update compression.

Stack: Python / C / CUDA / OpenMP / SIMD / APPFL

Case Study / GitHub

Lightweight Human Activity Recognition with Model Distillation

Teacher-student model distillation for wearable-sensor activity recognition, targeting efficient inference on edge devices.

Stack: Python / TensorFlow / Time-Series ML / Model Distillation / Edge AI

Case Study / GitHub

Stevens IT Quackathon: Data-Driven Ducks

A Spring 2025 Stevens IT Quackathon team concept for an AI academic and career guidance assistant.

Stack: Microsoft AI Technology / Recommendation Systems / NLP / Student Success

Project Page / Stevens Quackathon

Technical Focus

AI Systems Engineering Model Deployment Reinforcement Learning Sim2Real GPU / Systems Optimization Applied ML

Selected Writing

The notes section will collect implementation notes, experiment logs, and deployment writeups.