About Me
Perception AI Engineer with 2+ years of experience building production-grade autonomous driving perception systems, specializing in multi-sensor fusion, BEV-based 3D object detection, and embedded deployment. Proven track record of improving model accuracy and latency through geometry-aware learning, CUDA/TensorRT optimization, and end-to-end MLOps pipelines, and shipping perception stacks to vehicles under SIL/HIL and V-model processes. Recently applied imageconditioned generative vision models as an extension of perception expertise, focusing on spatial alignment, consistency, and controllable generation, without shifting away from core perception and robotics fundamentals.

