Key Responsibilities Develop vision and 3D perception algorithms using deep learning and geometric methods. Work with point clouds, depth data, and multimodal fusion (camera + LiDAR). Build and maintain calibration pipelines (camera, LiDAR, IMU). Implement production-quality code in C++ and Python. Optimize models for real-time or embedded platforms (quantization, pruning, GPU tuning). Deploy and maintain inference pipelines for cloud or edge devices. Collaborate across teams to integrate perception into production systems. Required Qualifications Strong background in computer vision, deep learning, or 3D perception. Experience with CNNs, transformers, and point cloud/3D vision methods (stereo, depth, SLAM). Proficiency in Python and C++ for algorithm and system development. Hands-on calibration experience (intrinsic/extrinsic, LiDAR-camera, IMU). Experience with PyTorch or TensorFlow. Model optimization and deployment on GPUs or embedded devices (Jetson, ARM, accelerators). Preferred ...