Description
Rohlik is hiring a Machine Learning Engineer to build and evaluate a human-video-to-robot-policy pipeline for its autonomous grocer. The role owns the capture specification, ground-truth hand-pose measurement, evaluation harness, and the first training runs on warehouse footage, while also reproducing published robot-learning claims and directing agents for data plumbing. It requires PyTorch, computer vision, 3D geometry, camera calibration, pose estimation, SLAM, robot-learning policies, and familiarity with ROS 2, with no publication record required.
