Senior Applied Scientist

Amazon • San Francisco, CA

1d • $192,200 - $260,000 • Onsite

About The Position

Amazon is seeking a world-class Sr. Applied Scientist to lead the development of next-generation object tracking systems for autonomous robots operating at Amazon's scale. In this role, you will architect robust, real-time tracking pipelines that fuse information across multiple sensor modalities — combining the rigor of classical estimation theory with the power of modern learning-based approaches to deliver tracking systems that are accurate, reliable, and scalable in complex, dynamic environments.

Amazon is on a mission to redefine the future of automation — and we're looking for exceptional talent to help lead the way. We are building the next generation of advanced robotic systems that seamlessly blend cutting-edge AI, sophisticated control systems, and novel mechanical design to create adaptable, intelligent automation solutions capable of operating safely alongside humans in dynamic, real-world environments.

We leverage the power of machine learning, artificial intelligence, and advanced robotics to solve some of the most complex operational challenges at a scale unlike anywhere else in the world. Our fleet of robots spans hundreds of facilities globally, working in sophisticated coordination to deliver on our promise of customer excellence — and we're just getting started.

As a Sr. Applied Scientist working on Tracking and Sensor Fusion, you will own the design and delivery of tracking systems that enable robots to maintain persistent, accurate awareness of objects, humans, and dynamic elements in their environment. You will bring deep expertise in multi-sensor fusion, Bayesian estimation, and Kalman filtering — paired with a strong command of modern learning-based tracking methods — to build systems that are both principled and adaptive.

Your work will be foundational to safe and intelligent robot behavior: enabling downstream planning, navigation, and manipulation systems to operate with confidence in the presence of uncertainty and change. You will lead research that bridges classical state estimation with data-driven approaches, collaborating with world-class teams pushing the boundaries of robotic perception, autonomy, and human-robot interaction.

Join us in building intelligent tracking and fusion systems that will define the future of autonomous robotics at scale.

Requirements

• PhD in computer science, electrical engineering, or related field
• 5+ years of experience in object tracking, sensor fusion, or state estimation for autonomous systems
• Deep expertise in Bayesian estimation and filtering — including Kalman Filters (EKF, UKF), Particle Filters, and multi-hypothesis tracking
• Strong experience with multi-sensor fusion across heterogeneous sensor suites (camera, LiDAR, radar, IMU)
• Demonstrated experience with learning-based tracking approaches (e.g., neural association, graph neural networks for tracking, attention-based trackers, learned motion prediction)
• Proficiency in Python and/or C++; experience with deep learning frameworks (PyTorch, TensorFlow, or equivalent)
• Proven track record of delivering tracking/fusion systems to production
• Strong publication record in top-tier computer vision, robotics, or ML venues

Nice To Haves

• Experience in the autonomous driving industry, particularly in developing and deploying real-time object tracking and sensor fusion pipelines for self-driving vehicles
• Hands-on experience building production-grade 3D multi-object tracking systems
• Experience with foundation models or large pre-trained representations applied to tracking or temporal reasoning
• Knowledge of graph-based optimization, factor graphs (GTSAM, Ceres), or probabilistic graphical models
• Experience with sim-to-real transfer and synthetic data generation for tracker training and evaluation
• Familiarity with tracking benchmarks and datasets (nuScenes, KITTI, Waymo Open Dataset, MOT Challenge, Argoverse)
• Experience with real-time systems, latency-constrained inference, and edge deployment
• Knowledge of SLAM, localization, or mapping systems and their interaction with tracking
• Experience with ROS/ROS2 and real-time robotics middleware

Responsibilities

• Lead the research, design, and development of multi-object tracking (MOT) systems for autonomous robots, combining classical and learning-based approaches
• Develop and deploy sensor fusion pipelines that integrate data from cameras, depth sensors, radar, IMUs, and other sensor modalities using principled estimation frameworks (Extended Kalman Filters, Unscented Kalman Filters, Particle Filters, factor graphs)
• Pioneer learning-based tracking methods including neural data association, learned motion models, transformer-based trackers, and end-to-end differentiable tracking architectures
• Design robust track management systems — including track initialization, association, occlusion handling, re-identification, and track lifecycle management
• Develop and validate tracking systems that operate reliably in real-time under challenging conditions: occlusion, clutter, sensor noise, and dynamic scene changes
• Collaborate closely with Perception, Navigation, Planning, and Controls teams to deliver integrated autonomy solutions
• Establish benchmarks, evaluation frameworks, and safety validation protocols for tracking systems
• Mentor scientists and engineers; foster a culture of scientific rigor, innovation, and high-impact delivery
• Publish research findings in top-tier venues (CVPR, ICCV, ECCV, ICRA, NeurIPS, etc.) and contribute to patents

Benefits

• health insurance (medical, dental, vision, prescription, Basic Life & AD&D insurance and option for Supplemental life plans, EAP, Mental Health Support, Medical Advice Line, Flexible Spending Accounts, Adoption and Surrogacy Reimbursement coverage)
• 401(k) matching
• paid time off
• parental leave
• sign-on payments
• restricted stock units (RSUs)

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Ph.D. or professional degree