Senior Applied Scientist, Amazon Industrial Robotics

Amazon Amazon · Big Tech · Seattle, WA · Research Science

Senior Applied Scientist role focused on developing next-generation advanced robotics systems that combine AI, control systems, and mechanical design for automation at Amazon's scale. The role involves research and implementation of deep learning and LLMs for robotics, with a focus on simulation, physics-based modeling, and sim-to-real gap reduction.

What you'd actually do

  1. Collaborate with simulation and robotics experts to translate physical modeling needs into robust, scalable, and maintainable simulation solutions.
  2. Design and implement high-performance simulation modeling and tools for rigid and deformable body simulation.
  3. Identify and optimize performance bottlenecks in simulation pipelines to support real-time and batch simulation workflows.
  4. Help build validation and unit testing pipelines to ensure correctness and physical fidelity of simulation results.
  5. Identify potential sources of sim-to-real gaps and propose modeling and numerical approximations to reduce them.

Skills

Required

  • PhD, or PhD and 4+ years of CS, CE, ML or related field experience
  • Strong programming skills in modern Python and/or C++
  • experience with GPU programming (CUDA, Warp, or similar)
  • Experience with robotics simulation environments such as MuJoCo, Newton, Drake and/or Isaac Lab
  • Expertise in one or more of the following: Solid foundation in numerical methods for multibody dynamics, frictional contact, Finite Element Method (FEM), Material Point Method (MPM) or other approaches for physics-based simulation
  • Experience implementing scientific or simulation software in a collaborative, production-quality codebase
  • Proficiency in linear algebra, differential equations, and numerical analysis

Nice to have

  • Experience programming in Java, C++, Python or related language
  • Experience working effectively across cross-functional teams and partnering well with people at all levels within an organization
  • PhD in simulation
  • Experience in one or more of the following: bimanual manipulation, imitation learning for dexterous manipulation, reinforcement learning for locomotion, teleoperation systems for data collection

What the JD emphasized

  • advanced robotics
  • AI
  • deep learning
  • large language models
  • robotics simulation
  • physics-based simulation
  • sim-to-real gaps

Other signals

  • advanced robotics
  • AI
  • deep learning
  • large language models
  • intelligent robotics systems
  • human-robot collaboration