Hiring: Principal Applied Scientist Perception, Compass Company: Amazon Location: Pasadena, CA Job Posted Time: 2026-09-09 17:58:26 Employment Type: Full-time Target Skills & Keywords : Perception, Robotics, Embodied AI, 3D Scene Understanding, Motion Prediction, Occupancy Forecasting, Semantic Scene Representation, Control Barrier Functions, Safety-Critical Autonomy, Foundation Models, LiDAR, Depth Cameras, RGB, Radar, Python, C++, Sensor Fusion, Uncertainty Quantification, Motion Planning, Reinforcement Learning Experience: - PhD in Electrical Engineering, Computer Science, Mathematics, or a related technical field - 6+ years of experience in perception research and development, with a significant portion in robotics or embodied AI - 10+ years of relevant work experience preferred - Proven track record of publications at top-tier venues (e.g., CVPR, ICCV, ECCV, NeurIPS, ICRA, RSS, CoRL) - Experience deploying perception systems on physical robots operating in unstructured or human-shared environments - Demonstrated ability to set technical direction and influence across teams at a senior level Required Skills: - Deep expertise in one or more of: 3D scene understanding, object detection and tracking, motion prediction, occupancy forecasting, or semantic scene representation - Proficiency in Python and C++ with experience writing production-grade perception code - Developing novel perception algorithms for real-time, predictive representations of dynamic environments (human motion forecasting, obstacle trajectory prediction, scene evolution modeling) - Designing perception outputs tightly coupled to safety constraints (control barrier functions) - Quantifying and bounding perception uncertainty with calibrated confidence estimates - Architecting perception pipelines that generalize across sensor modalities (LiDAR, depth cameras, RGB, radar) and robot morphologies - Applying foundation models and large-scale pre-training to safety-critical perception tasks - Collaborating with controls, motion planning, and firmware teams on interface contracts - Publishing research at top-tier venues and mentoring applied scientists and research engineers Qualifications: - Define and drive the long-term scientific vision for safety-critical perception within Compass across multiple robot platforms and deployment environments - Set scientific direction for perception and influence Amazon Robotics' safety architecture at the organizational level - Develop novel approaches to environment understanding that go beyond static scene representation - Provide real-time, predictive models of how humans, objects, and dynamic obstacles evolve over short time horizons - Replace conservative assumptions with precise, learned understandings of risk to unlock robot performance - Represent Amazon Robotics in the broader academic and industry community - Mentor and develop a team of applied scientists and research engineers Compensation: Not specified in the job posting. Interested candidates, please apply directly through the job posting on company's career page or try via AI auto apply on this platform. Don’t miss this opportunity to join a forward-thinking team!