Amazon
Robotics Applied Scientist
$172K–$222K
Sunnyvale, CA · Full-time · Posted Oct 26, 2026
About the job
Develop and deploy tactile- and force-feedback manipulation policies for dexterous robotic hands, from research and simulation through evaluation on physical hardware.
What you'll do
- Design and train policies for grasping and contact-rich manipulation; drive sim-to-real transfer to robotic hands.
- Build simulation and on-robot evaluation frameworks, and account for real motor and actuator constraints in control strategies.
- Lead research projects through deployment, collaborate across hardware and software teams, and publish and mentor.
What they ask for
- Programming experience in Java, C++, Python or a related language.
- Research or applied experience in tactile sensing, manipulation policy learning, contact-rich manipulation, dexterous grasping, or multi-modal perception for robotics.
- Experience deploying learned policies or control algorithms on physical robotic hardware.
Nice to have
- Hands-on experience with tactile sensing hardware and tactile signal processing.
- Experience with reinforcement learning, imitation learning, or foundation models for contact-rich manipulation and sim-to-real transfer.
Pay
171,600.00 - 222,200.00 USD annually (base salary)
Tools
Java, C++, Python, Isaac, MuJoCo, URDF
AI focus
Research and build reinforcement-learning, imitation-learning, or hybrid manipulation policies using tactile and force feedback; transfer and evaluate them on real robotic hardware.
Model-written summary · the original posting is authoritative