Welcome to Home Page

I am an AI Computer Vision Engineer with hands-on experience across the full lifecycle of vision system development, from applied research and model design to production deployment on Edge and Linux-based platforms. My core expertise includes Python, PyTorch, TensorFlow, OpenCV, NumPy, and C/C++, along with strong experience in CI/CD workflows, data versioning, and experiment management using Git, GitHub Actions, DVC, SSH, and WebDAV. 

I hold a Ph.D. in computer vision, where my research focused on segmentation-based deep tracking for intelligent video surveillance systems. This work strengthened my background in object detection, segmentation, multi-object tracking, and spatiotemporal analysis, and led to publications in high-impact journals. 

In industry, I focus on turning research ideas into scalable, high-performance vision pipelines. I work extensively with PyTorch, TensorFlow, Keras, and CUDA-optimized inference, and regularly build, test, and deploy models in Dockerized environments. My development and experimentation workflow relies on VSCode, Anaconda, and Vi, enabling efficient prototyping, evaluation, and iteration. I have also built automated testing and evaluation frameworks to ensure model reliability in real-world deployments. 

I work well in collaborative, cross-functional teams, combining clear technical communication with structured problem-solving and reproducible research practices. My goal is to build robust and scalable computer vision systems that perform reliably in real-world applications.