Senior Robotics Scientist, Tactile Manipulation

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

Job summary

Amazon is seeking a Senior Applied Scientist to develop tactile- and force-driven manipulation policies for dexterous multi-fingered hands. You will research policy learning algorithms enabling grasping and in-hand manipulation in unstructured environments, using touch and force feedback as primary signals.

You will drive sim-to-real transfer, collaborate across hardware and controls teams, and contribute to publishing and mentoring within a world-class robotics group.

Qualifications

• PhD or Master’s degree plus 6+ years of applied research experience.
• Experience programming in Java, C++, Python or related language.
• Research or applied experience in tactile sensing, manipulation policy learning, dexterous manipulation, or multi-modal perception for robotics.
• Experience deploying learned policies or control algorithms on physical robotic hardware.

Responsibilities

• Design and train manipulation policies that leverage tactile and force feedback for dexterous grasping, in‑hand manipulation, and contact‑rich tasks.
• Drive sim‑to‑real transfer, closing the gap between simulated and physical performance on real robotic hands.
• Shape objectives and control strategies with hardware in mind, accounting for actuator dynamics and thermal limits.
• Build simulation‑based and on‑robot evaluation frameworks with benchmarks for tactile sensing and policy performance.
• Own scientific and technical projects within tactile sensing and manipulation workstreams, guiding a workstream.

Skills

Java

C++

Python

Robotics research

Education

PhD or Master’s degree

Tools

MuJoCo

URDF

Isaac

Job description

Amazon is seeking a Senior Applied Scientist to develop tactile- and force-driven manipulation policies for dexterous multi-fingered hands. You will research policy learning algorithms enabling grasping and in-hand manipulation in unstructured environments, using touch and force feedback as primary signals.

You will drive sim-to-real transfer, collaborate across hardware and controls teams, and contribute to publishing and mentoring within a world-class robotics group.