Robotics Automation Perception Engineer

Telexistence

ML

Vision

Python

PyTorch

Robotics

About this role

This engineer develops perception for TX GHOST, a robot performing autonomous pick-and-place work in Japanese convenience stores. RGB, depth and other data from deployed robots are used to improve performance in changing retail environments.

Work covers deep-learning and computer-vision algorithms, quantitative analysis, safe deployment, and optimization for constrained hardware. Tasks include detection, segmentation, keypoints, 3D pose or reconstruction, augmentation, and acceleration with TensorRT or TorchScript. Core tools are Python, PyTorch, OpenCV, NumPy and SciKit.

Candidates need at least three years developing perception systems or equivalent academic research, strong debugging and monitoring, low-level vision and ML depth, experience implementing modern methods from scratch, RGB plus depth or LiDAR work, customization of deep-learning applications, and speed or latency optimization.

This is an AI-generated summary of the employer's original posting — details can be incomplete, out of date or simply wrong. Always confirm everything on the official posting before applying.