Senior Robot Learning Engineer: Real-World Policy & Control

Lightspeed; Northbrook (IL); On-site; USD 140,000 - 210,000; Full time

Job summary

LightSpeed Build Technologies seeks a Senior Robot Learning Engineer to own how our robots learn and perform physical skills, building data pipelines, policies, and the executor that runs every action on real hardware.

You will train with imitation learning, diffusion or transformer policies, work in simulation and on live robots, and guide teams to push deformable-material manipulation, safety and real-time deployment.

Qualifications

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

Responsibilities

• Define how we capture demonstrations: teleoperation rigs and egocentric capture of people doing the work.
• Own the data pipeline: synchronized observations and actions, episode labelling, dataset versioning and quality checks.
• Decide what data each new task needs, and how failures are labelled and fed back.
• Set the policy architecture: a shared vision and force backbone with task-conditioned heads.
• Train with imitation learning, diffusion or transformer policies and vision-language-action models; use reinforcement learning where the reward can be clearly defined.
• Build the training and evaluation loop, in simulation and on real robots, with held-out evaluations that gate deployment.
• Solve manipulation of deformable materials: cable, tape, membrane.
• Set coverage and first-pass yield targets per skill, and measure against them.
• Own the actuate executor: classical control and learned policies behind one contract, so the planner can choose either for each step.
• Build the compliance layer for contact-rich work: nailing, pressing, taping, mudding, insertion, with force and impedance control.
• Build recovery behaviours for the common failures of each primitive.
• Deploy policies on the robot within real-time and safety limits.
• Define what each tool must sense and report, so its actions can be learned from and controlled.
• Co-own the foundation interfaces with the world sensing and agentic planning principals, and own the data and evaluation interface.
• For each new trade: collect demonstrations, train and evaluate the policy, add recovery.
• Drive down the time it takes to teach a new trade.
• Set robot learning and control architecture across both robot families.
• Lead and mentor learning and manipulation engineers.
• Make the system something engineers can teach new trades with, without you in the loop.
• Stay hands-on: write production code and test on real robots every week.

Skills

Robotics

Machine Learning

Imitation learning

Reinforcement learning

Python

C++

ROS2

Linux

Docker

CI/CD

Education

MS or PhD in Robotics/ML/CS

Tools

PyTorch

ROS2

Docker

Linux

MuJoCo

Isaac Sim

Job description

LightSpeed Build Technologies seeks a Senior Robot Learning Engineer to own how our robots learn and perform physical skills, building data pipelines, policies, and the executor that runs every action on real hardware.

You will train with imitation learning, diffusion or transformer policies, work in simulation and on live robots, and guide teams to push deformable-material manipulation, safety and real-time deployment.