Robot Learning Engineer (Manipulation)

Join Applied Intuition, a company dedicated to building a robot learning platform for industrial tasks. As a Robot Learning Engineer, you will work on manipulation policies, train and fine-tune them, and deploy them on physical robots. You will have the opportunity to work hands-on with hardware and see your work reach customers. The position offers a range of benefits, including health insurance, a fitness stipend, a 401(k) match, a learning stipend, and parental leave.

Experience with bimanual manipulation, force-controlled insertion, tactile sensing, or dexterous hands

Responsibilities

• Travailler sur l'ensemble du cycle d'apprentissage pour les tâches de manipulation, de la définition de la tâche à la démonstration, en passant par la collecte de données, l'entraînement, l'évaluation sur robot réel et le déploiement.
• Former et affiner les politiques de manipulation, en choisissant la bonne approche pour chaque tâche, et développer des recettes répétables pour des tâches industrielles telles que la prise et le placement.
• Déployer des politiques sur des systèmes informatiques embarqués et valider le traitement des observations, les interfaces d'action et le timing de contrôle sur le robot.
• Working knowledge of robot kinematics, coordinate frames, camera calibration, and the interface between learned actions and low-level control
• Strong Python and PyTorch skills, with the ability to write maintainable training, evaluation, and deployment code
• The habit of diagnosing failures with controlled experiments across data, sensing, model, and execution
• Trained or fine-tuned a learned manipulation policy and deployed and evaluated it on a physical robot

Requirements

• Practical depth in imitation learning and at least one modern policy family, such as vision-language-action models, diffusion policies, or action-chunking transformers

1+ years of professional experience

• A Bachelor's degree in Computer Science, Software Engineering, or equivalent
• Comfort taking on open-ended problems and communicating tradeoffs clearly to teammates at the robot
• Don’t meet every single requirement? If you’re excited about this role but your past experience doesn’t align perfectly with every qualification in the job description, we encourage you to apply anyway. You may be just the right candidate for this or other roles
• Experience with ROS 2, LeRobot, or simulators such as Isaac and MuJoCo
• Experience with reinforcement learning post-training, learning from interventions, or transferring policies across robot platforms

Preferred

• Experience optimizing inference on NVIDIA Jetson or GPU edge systems, including model export, compilation, or quantization

Pay

USD 150,000 - 300,000