Tech Stack

Description

You will design and implement key components of a multi-modal perception system for autonomous middle-mile logistics. This includes object detection, tracking, multi-sensor fusion, and building scalable training and evaluation infrastructure. Your work directly powers fleet of autonomous trucks deployed with Fortune 500 retailers.

Requirements

• Masters/PhD in CS, EE, Robotics or related field
• 7+ years of related experience
• 2+ years professional experience in Computer Vision using C++ and OpenCV
• Expert knowledge of modern C++ (C++11+) and Python

Responsibilities

• Design and implement perception system components (object detection, tracking, multi-sensor fusion)
• Build software infrastructure for learning algorithms using large image/LIDAR data
• Design optimized pipelines for data preprocessing, training, postprocessing, and inferencing
• Train perception models, evaluate performance, and fix bottlenecks
• Develop scalable training/evaluation tools and collaborate on system integration tests