Robot Learning Engineer: Master Teleoperation & Policies

Lightspeed; Northbrook (IL); On-site; USD 120,000 - 170,000; Full time

Benefits offered by this job

Competitive compensation

Comprehensive benefits

Hands-on culture

Job summary

LightSpeed is building AI-powered robotics to transform construction. As a Robot Learning Engineer, you will lead the path from human demonstration to deployed robot behavior, shaping data pipelines and training policies for dexterous manipulation.

You will work with VR tracking, real hardware, and simulation to optimize teleoperation and policy learning, reporting to the robotics team in a fast-moving environment.

Qualifications

• 3+ years of hands-on experience in robot learning, ML for robotics, or closely related production ML.
• Experience training policies from demonstrations on physical robots using imitation learning.
• Experience collecting teleoperation or demonstration data for robot learning.
• Strong PyTorch skills and experience running training, evaluation, and debugging end to end.
• Track record of evaluating models in the real world and diagnosing failures.

Responsibilities

• Build and improve teleoperation pipelines using leader arms for bulk arm motion and VR hand tracking for fine interaction.
• Retarget human hand motion to a dexterous robot hand, developing in simulation first and validating on hardware.
• Design data collection protocols so demonstrations are consistent, well-structured, and train well.
• Train and fine-tune manipulation policies using imitation learning and vision-language-action models.
• Define and run evaluation protocols on real robots, measuring success rate per task step.

Skills

Python

PyTorch

C++

Linux

Docker

Git

ROS/ROS2

Imitation learning

Data collection protocols

Education

MS or PhD in Robotics, ML, CS

Tools

MuJoCo

Isaac Sim

rosbag

MCAP

LeRobot

Job description

LightSpeed is building AI-powered robotics to transform construction. As a Robot Learning Engineer, you will lead the path from human demonstration to deployed robot behavior, shaping data pipelines and training policies for dexterous manipulation.

You will work with VR tracking, real hardware, and simulation to optimize teleoperation and policy learning, reporting to the robotics team in a fast-moving environment.