About

I’m a 3D Perception Engineer focused on building advanced AI systems that understand the world through depth, geometry, and multi-sensor fusion.

I’ve implemented state-of-the-art models like PointNet from scratch for point cloud classification and segmentation, and I specialize in 3D object detection and tracking, BEV transformation, and sensor fusion. My experience covers LiDAR, stereo vision, point cloud processing, and solutions such as lane detection on LiDAR data, Point-Pixel fusion (early fusion), and Box-to-Box fusion (late fusion). I’ve also worked on Kalman filter–based tracking.

I’m passionate about applying cutting-edge research to real-world challenges in autonomous driving, robotics, and spatial AI.

I’m seeking freelance or full-time opportunities where I can contribute deep expertise in 3D perception and sensor fusion to build smarter machines that see and understand their environment.