Train, fine-tune, and evaluate state-of-the-art computer vision models (Object Detection, Instance Segmentation, Image Classification) using architectures like YOLOv8/v10.
Optimize and quantize heavy deep learning models to run at high FPS on resource-constrained Edge devices using NVIDIA TensorRT, DeepStream, or OpenVINO.
Deploy, test, and maintain models on edge hardware, primarily the NVIDIA Jetson family (Orin Nano/Xavier).
Build highly eJicient video ingestion and processing pipelines using OpenCV and GStreamer.
Leverage AI coding assistants (Copilot, Claude, Gemini) to write boilerplate code, debug rapidly, and accelerate deployment timelines.