About the job
We are seeking a Principal Applied Scientist to help develop the next generation of advanced robotics systems that will transform automation at Amazon's scale. We're building revolutionary robotic systems that combine cutting-edge AI, sophisticated control systems, and advanced mechanical design to create adaptable automation solutions capable of working safely alongside humans in dynamic environments. This is a unique opportunity to shape the future of robotics and automation at an unprecedented scale, working with world-class teams pushing the boundaries of what's possible in robotic dexterous manipulation, locomotion, and human-robot interaction. This role presents an opportunity to shape the future of robotics through innovative applications of deep learning and large language models.
Responsibilities
Define and drive the long-term scientific roadmap for whole body control and dexterous manipulation, working with autonomy and delivering artifacts that set the standard for scientific and engineering excellence
Serve as the primary technical authority on whole body control methods — including reinforcement learning, imitation learning, hierarchical quadratic programming, and model-predictive control — across the organization
Identify and tackle intrinsically hard, open-ended research problems in loco-manipulation, acquiring expertise as needed and proposing innovative solutions that span multiple teams
Collaborate with hardware and robotics leads to co-design systems for loco-manipulation, ensuring science solutions are grounded in real-world deployment constraints
Represent scientific capabilities to senior leadership and external partners; communicate complex technical concepts to both technical and non-technical audiences
Mentor and develop a community of Applied Scientists and engineers, raising the scientific bar across the organization
Qualifications
Minimum
PhD in Robotics, Computer Science, Mechanical Engineering, or a related field, with 7+ years of relevant research experience after degree; or Master's degree with 12+ years of equivalent experience
Deep expertise in whole body control methods, including hierarchical quadratic programming (HQP) and model-predictive control (MPC)
Proven experience with imitation learning and reinforcement learning applied to whole body control and manipulation
Experience developing and deploying real-time controllers on physical robotic hardware
Experience with simulation environments such as IsaacLab, MuJoCo, or Drake
Experience in state estimation from multiple sensor modalities
Demonstrated ability to influence technical strategy across multiple teams and organizations
Preferred
Experience co-designing hardware and algorithms for loco-manipulation systems
Strong record of mentoring scientists and engineers and growing high-performing teams
PhD in Robotics with a focus on whole body control or dexterous manipulation
Track record of publications and/or patents in robotics, control, or machine learning