Robots are about to step out of the movies and into our homes. If you're excited about this robotics revolution, come join Amazon's Personal Robotics Group. As an Applied Scientist in this org, you'll design and implement state-of-the-art algorithms that bridge Computer Vision, Metric-semantic Mapping, and Contextual Reasoning to create comprehensive 3D/4D scene understanding capabilities. Your work will directly impact how our intelligent system perceives and reasons about dynamic home environments, building rich world representations that enable safe and effective autonomous operation alongside family members. You'll push the state-of-the-art techniques in Robotics and design novel algorithms that bridge the gap between research and real-world deployment.

In this role, you'll develop expert models as well as end-to-end learning-based solutions that integrate Spatial Scene Understanding, Semantic Scene Graphs, and High-level Reasoning into unified world models. You'll leverage advanced Deep Learning techniques including Transformer architectures, Neural Radiance Fields, and Multi-modal Foundation Models to create robust representations of domestic spaces. Your solutions will need to handle the unique challenges of unstructured environments - from varying lighting conditions and cluttered spaces to dynamic interactions with humans and pets.

Key job responsibilities
- Develop multi-modal perception systems that fuse sensiing modalities in cluding but not limited to RGB-D, LiDAR, and other sensing modalities to create robust spatial-semantic world models.
- Design and implement advanced 3D/4D scene understanding systems using neural implicit representations, occupancy networks, and dynamic scene graphs
- Design experiments to identify the limitations of current state-of-the-art models and developing new models or techniques that can surpass these models
- Collaborate with engineering teams to optimize and scale models for real-world applications. Influence technical decisions and implementation strategies within your area of focus
- The ability to work with minimal guidance, be proactive and to handle ambiguity and the challenge of quickly evolving goals
- Communicate complex technical work to a non-technical audience


A day in the life
- Design Expert architectures and Train ML models for deployment in simulation and real-world robots, identify and document their limitations post-deployment
- Drive technical discussions within your team and with key stakeholders to develop innovative solutions to address identified limitations


About the team
The Personal Robotics Group is pioneering intelligent robotic products that deliver meaningful customer experiences. We're building the next generation of robotic systems that will redefine how customers interact with technology. This is a unique opportunity to shape the future of personal robotics working with world-class teams pushing the boundaries of what's possible in robotic Manipulation, Locomotion, and Open World Understanding.

Join us if you’re passionate about creating the future of personal robotics, solving complex challenges at the intersection of hardware and software, and seeing your innovation deliver transformative customer experiences.