Senior Applied Scientist, Computer Vision and Robotics, Robotics

Position: Senior Applied Scientist, Computer Vision and Robotics, Amazon Robotics
Come shape the future of robotic sensing hardware by building the computer vision and ML systems that define how every robot in Amazon's global fulfillment network sees, senses, and understands the world. This is applied science embedded in a hardware development team where you directly shape what gets built, manufactured, and deployed  a Senior Applied Scientist on the Amazon Robotics Sensing and Compute hardware team, you will be the ML and perception expert working alongside the Principal Applied Scientist and Principal Hardware Development Engineer to shape the future of deployed and scaled sensing hardware.

You will influence sensor selection, compute architecture, optical design, and system level trade offs, ensuring the hardware we build is purpose designed for the algorithms that run on it. You will help define what the next generation of cameras, depth sensors, and edge compute modules need to be, and then prove it with data, experimentation, and production validation.

What makes this role unique:

-Embedded in the hardware development team, directly influencing what gets designed, manufactured, and shipped-Partner with the Principal Engineers to co define the sensing and compute hardware roadmap for every major Amazon Robotics program-Own the ML experimentation and validation that drives hardware architecture decisions for cameras, depth sensors, and edge compute-Solve perception problems no other company is tackling: safety rated vision, multi modal sensor fusion, and real time inference on resource constrained hardware-Ship to hundreds of fulfillment sites worldwide across autonomous mobile robots, manipulation workcells, barcode sensing, and safety rated human collaborative systems-Your work does not sit in a research queue.

It goes into production hardware that enables the future of Amazon Robotics Key job responsibilities-Partner with the Principal Hardware Development Engineer and Principal Applied Scientist to co define sensing and compute hardware requirements, ensuring ML and perception needs drive sensor selection, optical design, compute architecture, and system level trade offs-Develop and optimize computer vision and deep learning models for robotic perception including object detection, depth estimation, scene understanding, and barcode recognition, purpose built for edge deployment on resource constrained hardware-Lead ML experimentation and validation that directly informs hardware architecture decisions for cameras, depth sensors, and edge compute modules-Design and execute benchmarking frameworks to evaluate sensing hardware performance across diverse robotic use cases, providing data driven recommendations on what to build next-Optimize models for production edge deployment including quantization, pruning, distillation, and inference pipeline tuning to meet strict latency, power, and accuracy requirements-Drive research and experimentation on next generation perception capabilities in collaboration with the Principal Applied Scientist, including multi modal sensor fusion, safety rated vision, and real time inference for autonomous and human collaborative robotics-Collaborate cross functionally with hardware engineers, software developers, and robotics program teams to transition models from prototype through production validation and fleet deployment-Contribute to the sensing and compute hardware roadmap alongside the Principal Applied Scientist, identifying where ML trends and emerging capabilities require new hardware architecture or sensor modalities-Mentor engineers and scientists on ML best practices for embedded systems and production robotics-Publish and present research to advance the state of the art in robotic perceptionA day in the life

In this role you will work at the intersection of machine learning and physical robotics hardware. You will collaborate with hardware engineers to evaluate how your models perform on real sensors and edge compute, run experiments that directly influence what gets built next, and validate perception systems alongside robotics program teams. You will push the boundaries of computer vision for robotic applications while seeing your work deploy on real robots in real fulfillment centers.

This is applied science with immediate, measurable impact at a scale no other robotics company can offer.

Amazon offers a full range of benefits that support you and eligible family members, including domestic partners. Benefits can vary by location, the number of…