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 at scale. As 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 perception A 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 regularly scheduled hours you work, length of employment, and job status such as seasonal or temporary employment. The benefits that generally apply to regular, full-time employees include: 1. Medical, Dental, and Vision Coverage 2. Maternity and Parental Leave Options 3. Paid Time Off (PTO) 4. 401(k) Plan If you are not sure that every qualification on the list above describes you exactly, we'd still love to hear from you! At Amazon, we value people with unique backgrounds, experiences, and skillsets. If you’re passionate about this role and want to make an impact on a global scale, please apply! About the team The Amazon Robotics Sensing and Compute team powers a customer centric ecosystem built for speed, quality, and innovation. We stay ahead of sensing and compute technology, standardize reusable and cost effective modules, and pair them with deep engineering expertise and a robust supply chain. Every customer gets the right solution, whether off the shelf, rapidly customized, or purpose built, easy to integrate and ready to scale. We are a small, fast moving team of builders who own the full stack from optics through edge compute and take pride in shipping production hardware that enables every major robotics program in Amazon's global fulfillment network. If you want your work to matter on day one, this is the team. - PhD, or Master's degree and 6+ years of applied research experience - Experience programming in Java, C++, Python or related language - Experience building complex software systems, especially involving deep learning, machine learning and computer vision, that have been successfully delivered to customers - Experience with one or more deep learning frameworks such as PyTorch, TensorFlow, or equivalent - Experience with 2D and 3D vision tasks including object detection, segmentation, depth estimation, or point cloud processing - Experience optimizing ML models for deployment on resource constrained hardware including quantization, pruning, or distillation techniques - Experience in written and verbal communication with the ability to present complex technical information in a clear and concise manner to executives and non-technical leaders - PhD, or PhD and 4+ years of deep learning, computer vision, human robotic interaction, algorithms implementation experience - Experience with robotic perception systems in industrial, warehouse, or manufacturing environments - -Experience with sensor fusion across multiple modalities (RGB, depth, lidar, time of flight) - -Familiarity with edge compute hardware and embedded inference pipelines - -Experience with real time computer vision systems operating under strict latency and power constraints - -Track record of transitioning research prototypes to production systems deployed at scale - -Experience with safety critical ML applications or functional safety requirements - -Experience collaborating with hardware engineering teams on sensor selection, optical design, or compute architecture trade offs - -Experience with image signal processing pipelines and camera system characterization - -Experience mentoring scientists or engineers in applied research environments Amazon is an equal opportunity employer and does not discriminate on the basis of protected veteran status, disability, or other legally protected status. Our inclusive culture empowers Amazonians to deliver the best results for our customers. If you have a disability and need a workplace acc