2 days ago
Base Salary
$172k - $223k/yr
Responsibilities
- Design and implement real-time Visual Inertial Odometry algorithms for robotic platforms.
- Develop multi-sensor fusion pipelines using cameras, IMUs, and other sensing modalities for pose tracking.
- Optimize perception and tracking algorithms for embedded ARM and GPU-accelerated hardware under latency and power constraints.
- Apply learned features, depth estimation, and neural odometry alongside classical geometric perception methods.
- Build calibration, evaluation, and benchmarking infrastructure for perception systems.
- Integrate perception outputs with hardware, controls, navigation, and robot autonomy teams.
- Lead projects from research prototyping through production deployment.
Requirements
- At least 3 years of experience building models for business applications.
- PhD, or a master's degree plus at least 4 years of experience in computer science, computer engineering, machine learning, or a related field.
- Patents or publications in top-tier peer-reviewed conferences or journals.
- Programming experience in Java, C++, Python, or a related language.
- Experience with algorithms and data structures, parsing, numerical optimization, data mining, parallel and distributed computing, or high-performance computing.
- Hands-on experience developing and deploying Visual Inertial Odometry or visual-inertial SLAM systems.
- Strong understanding of multi-sensor fusion and state estimation, including cameras, IMUs, odometry, EKF, and factor graphs.
- Experience optimizing perception algorithms for embedded or resource-constrained hardware.
- Hands-on experience with real sensor data, calibration, and physical robot platforms.
- Familiarity with modern machine-learning approaches to perception, including learned feature extraction, depth prediction, and end-to-end odometry.
- Preferred experience with Unix/Linux, professional software development, real-time systems programming, performance profiling, ARM/GPU platforms, legged robots, stereo vision, camera-IMU calibration, time synchronization, and sensor characterization.
- Preferred track record of shipping VIO or SLAM systems to production robots at scale.
- Preferred experience with NVIDIA Jetson, Qualcomm RB5, or similar embedded AI platforms and familiarity with ROS/ROS2.
- Preferred publication record at robotics or computer-vision conferences and history of technical leadership and cross-functional collaboration.
Benefits
- Amazon offers health insurance including medical, dental, vision, prescription, life and AD&D coverage, an Employee Assistance Program, mental health support, a medical advice line, flexible spending accounts, and adoption and surrogacy reimbursement.
- Benefits include 401(k) matching, paid time off, and parental leave.
- The position is based in New York, New York, USA.
