Robot Learning Engineer - Manipulation

Applied Intuition•Sunnyvale, CA

18h•Onsite

About The Position

Applied Intuition is building a robot learning platform on Dana, its physical AI platform: the data infrastructure and training intelligence a company needs to make any robot learn an industrial task and keep improving it. The robotics team builds that platform and uses it to deliver robot autonomy on customer lines, training, evaluating, and deploying policies on real robots doing real industrial tasks. Everyone on the team works hands-on with hardware and sees their work reach customers. As a Robot Learning Engineer, you will work on manipulation policies from task definition to a policy running reliably on a physical robot. You will train and fine-tune policies, understand why they fail, and make them dependable enough for customer use. Success is measured on the robot, not only on offline benchmarks. We are open to candidates at different experience levels who meet the requirements. We value demonstrated work on real systems, including equivalent practical experience, over a particular degree or title.

Requirements

Trained or fine-tuned a learned manipulation policy and deployed and evaluated it on a physical robot.
Strong Python and PyTorch skills, with the ability to write maintainable training, evaluation, and deployment code.
Practical depth in imitation learning and at least one modern policy family, such as vision-language-action models, diffusion policies, or action-chunking transformers.
Working knowledge of robot kinematics, coordinate frames, camera calibration, and the interface between learned actions and low-level control.
The habit of diagnosing failures with controlled experiments across data, sensing, model, and execution.
Comfort taking on open-ended problems and communicating tradeoffs clearly to teammates at the robot.

Nice To Haves

Experience with bimanual manipulation, force-controlled insertion, tactile sensing, or dexterous hands.
Experience with ROS 2, LeRobot, or simulators such as Isaac and MuJoCo.
Experience optimizing inference on NVIDIA Jetson or GPU edge systems, including model export, compilation, or quantization.
Experience with reinforcement learning post-training, learning from interventions, or transferring policies across robot platforms.

Responsibilities

Work on the full learning loop for manipulation tasks: task definition, demonstration collection, data curation, training, real-robot evaluation, and deployment.
Train and fine-tune manipulation policies, from large pretrained models such as vision-language-action models to compact task-specific policies, and choose the right approach for each task.
Develop repeatable recipes for industrial tasks such as pick-and-place, bimanual handling, and contact-rich assembly, adding force or tactile signals where they help.
Deploy policies on edge compute and validate observation processing, action interfaces, and control timing on the robot.
Turn failures and human interventions into better data, better models, and better evaluation.
Measure what customers care about, including success rate, cycle time, intervention rate, and the data and time needed to reach a target, and improve those numbers task after task.
Package recipes and models so the next task, and the next robot, starts from what was learned on the last one.