Amazon
Applied Scientist - Perception (SLAM/VIO), Fauna
$172K–$223K
New York, NY · Full-time · Posted Oct 19, 2026
- Experience
- 3+ years of building models for business application; PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience.
- Education
- PhD, or Master's degree and 4+ years of CS, CE, ML or related field experience.
About the job
Develops and deploys visual-inertial odometry, sensor-fusion, and machine-learning perception systems for real-time robotic state estimation on physical robots.
What you'll do
- Design VIO and multi-sensor fusion algorithms for real-time pose tracking.
- Optimize, test, and deploy perception systems on embedded robotic hardware; build calibration and benchmarking infrastructure.
- Integrate learned perception methods with geometric approaches and collaborate across robotics teams.
What they ask for
- Hands-on experience developing and deploying Visual Inertial Odometry or visual-inertial SLAM systems.
- Strong understanding of multi-sensor fusion and state estimation.
- Experience optimizing perception algorithms for embedded or resource-constrained hardware, with real sensor data, calibration, and physical robot platforms.
- Experience programming in Java, C++, Python or a related language; experience in patents or top-tier peer-reviewed publications.
Nice to have
- Experience using Unix/Linux.
- Experience with ROS/ROS2.
Pay
USD 172,400.00 - 223,400.00 annually (base salary)
Tools
Java, C++, Python, Unix/Linux, ARM, GPU, NVIDIA Jetson, ROS/ROS2
AI focus
Apply modern ML-based perception, including learned features, depth estimation, and neural odometry, to complement geometric methods.
Model-written summary · the original posting is authoritative