✦ Luna Orbit — AI & Machine Learning

Applied Scientist II, Industrial Robotics Group

at Amazon.com

📍 US, MA, N.reading Hybrid Posted March 29, 2026
Type Full-Time
Experience mid
Exp. Years PhD
Education PhD
Category AI & Machine Learning

Applied Scientist II in the Industrial Robotics Group developing ML-based robotic manipulation systems for Amazon-scale automation, integrating classical methods with learning-based approaches.

  • Lead design, adapt, and implement novel machine learning solutions for manipulation robots
  • Create hybrid approaches combining classical methods with learning-based solutions
  • Design learning algorithms for automated parameter tuning and adaptation
  • Develop data collection pipelines for demonstrations
  • Build and test prototype workcell setups

Emphasis on ML for robotics, hybrid learning methods, data collection for demonstrations, and real-time control considerations with C++/Python/Java and Unix/Linux environments.

We seek a PhD-level applied scientist with a strong machine learning background focused on robot manipulation, imitation and reinforcement learning, and proficiency in Python/C++/Java with Unix/Linux for real-world robotics applications.

PhDExperience programming in JavaC++Python or related languageExperience in algorithms and data structuresparsingnumerical optimizationdata miningparallel and distributed computinghigh-performance computing
Unix/LinuxExperience in professional software developmentPhD in RoboticsComputer Scienceor related fieldImitation learning or reinforcement learningRobot control systemsReal-time control systemsRobot motion planningML frameworksDemonstration-based learning and data collection
Unix/LinuxPythonC++Java
PhDJavaC++Pythonalgorithmsdata structuresparsingnumerical optimizationdata miningparallel and distributed computinghigh-performance computingUnix/Linuximitation learningreinforcement learningrobot controlrobot motion planningmachine learningdata collection pipelinesdemonstrations
PhDJavaC++Pythonalgorithmsdata structuresparsingnumerical optimizationdata miningparallel and distributed computinghigh-performance computingUnix/Linuximitation learningreinforcement learningrobot controlrobot motion planningmachine learningdata collection pipelinesdemonstrations
CollaborativeStrong communicationProblem solvingTeamwork
Industry Technology
Job Function Develop/industrialize machine learning for robotic manipulation and control in real-world settings.
Role Subtype Applied Scientist
Tech Domains Python, Java, C++, Unix/Linux
applied scientistindustrial roboticsmachine learningroboticsmanipulationdexterous taskshybrid methodslearning algorithmsimitation learningreinforcement learningrobot controlrobot motion planningdata collection pipelinesdemonstrationsunix/linuxpythonc++java

No PhD, Lack of experience with imitation or reinforcement learning, No hands-on experience with robot control or real-time systems

Apply for this Position →

Get matched to jobs like this

Luna finds roles that fit your skills and career goals — no endless scrolling required.

Create a Free Profile