Senior Applied Scientist: Tactile Robotics & Manipulation

Amazon Inc.; Sunnyvale (CA); On-site; USD 192,000 - 260,000; Full time

Job summary

Amazon.com Services LLC is seeking a Senior Applied Scientist to develop tactile- and force-driven manipulation policies for highly dexterous hands, combining reinforcement learning, imitation learning, and real hardware. You will drive sim-to-real transfer and collaborate with hardware, mechanical design, firmware, and controls teams to deploy advanced robotic capabilities at scale.

This role offers opportunities to publish, mentor, and shape sensor and actuator design decisions while advancing

Qualifications

• PhD or master’s degree with 6+ years of applied robotics research.
• Proficiency in Java, C++, and Python.
• Experience in tactile sensing, manipulation policy learning, or multi-modal perception.
• Experience deploying policies on real robotic hardware.

Responsibilities

• Design and train manipulation policies that leverage tactile and force feedback for dexterous grasping and in-hand manipulation.
• Drive sim-to-real transfer between simulation and real hardware.
• Shape objectives and control strategies considering motors, transmission, backdrivability, and thermal limits.
• Build simulation-based and on-robot evaluation frameworks with benchmarks.
• Own scientific projects in tactile sensing and manipulation, guiding a workstream.
• Collaborate with hardware, mechanical design, firmware, and controls teams to translate research into deployable capabilities.
• Publish at top venues and foster external collaborations.
• Mentor engineers and interns on real-world manipulation and sensing problems.

Skills

Java

C++

Python

Reinforcement learning

Imitation learning

Policy learning

Robotics

Education

PhD, or Master's degree and 6+ years of applied robotics research experience

Tools

MuJoCo

Isaac

Job description

Amazon.com Services LLC is seeking a Senior Applied Scientist to develop tactile- and force-driven manipulation policies for highly dexterous hands, combining reinforcement learning, imitation learning, and real hardware. You will drive sim-to-real transfer and collaborate with hardware, mechanical design, firmware, and controls teams to deploy advanced robotic capabilities at scale.

This role offers opportunities to publish, mentor, and shape sensor and actuator design decisions while advancing