Senior Robot Learning Engineer — Real-World Robotics

LightSpeed Photonics Pvt. Ltd.; Northbrook (IL); On-site; USD 120,000 - 190,000; Full time

Job summary

LightSpeed Build Technologies seeks a Senior Robot Learning Engineer to own how robots learn and perform tasks. You will design data capture, policy architectures and the execution layer that runs both classical and learned control on real robots, including deformable-material handling and high-variance assembly.

You will train policies with imitation learning, diffusion or transformers, and you will drive the data pipeline from demonstrations to evaluation, collaborating with sensing and

Qualifications

• 5+ years in robotics or machine learning with real hardware deployments.
• Deep experience with imitation learning and reinforcement learning.
• Force and impedance control for contact-rich manipulation.
• Built a data pipeline for robot learning: teleoperation capture, labeling, versioning and evaluation.
• Deep learning in PyTorch, from dataset to deployed policy.

Responsibilities

• Define data capture methods via teleoperation rigs and egocentric demonstrations.
• Own the data pipeline: synchronized observations, labeling and dataset versioning.
• Set policy architecture and train with imitation learning, diffusion or transformer methods.
• Build training/evaluation loop in simulation and on real robots with gate evaluations.
• Deploy policies on robots within real-time and safety constraints.
• Lead and mentor learning engineers and define cross-team technical direction.

Skills

Python

C++

ROS2

Linux

Docker

CI/CD

PyTorch

Imitation learning

Reinforcement learning

Robot learning pipelines

Education

MS or PhD in Robotics, Machine Learning, Computer Science or related field

Tools

Isaac Sim

MuJoCo

rosbag

Job description

LightSpeed Build Technologies seeks a Senior Robot Learning Engineer to own how robots learn and perform tasks. You will design data capture, policy architectures and the execution layer that runs both classical and learned control on real robots, including deformable-material handling and high-variance assembly.

You will train policies with imitation learning, diffusion or transformers, and you will drive the data pipeline from demonstrations to evaluation, collaborating with sensing and