Applied Scientist - Perception (SLAM/VIO), Fauna - New York

Sourced from educativ.net

Amazon’s Fauna team is seeking an Applied Scientist to design and optimize Visual Inertial Odometry (VIO) and multi-sensor fusion systems for autonomous robots. You will develop state estimation algorithms that run efficiently on resource-constrained embedded hardware, blending classical geometric techniques with modern deep learning approaches. This hands-on role involves prototyping, testing, and deploying perception pipelines directly onto physical robotic platforms like Sprout.

• Design and implement VIO and SLAM algorithms for real-time robotic state estimation
• Develop multi-sensor fusion pipelines integrating cameras, IMUs, and other sensing modalities
• Optimize perception algorithms for embedded hardware under strict latency and power constraints
• Integrate modern ML-based perception techniques with classical geometric methods
• Build calibration, evaluation, and benchmarking infrastructure for perception systems
• Collaborate with hardware, controls, and navigation teams to deploy autonomy stacks

• PhD or Master’s degree plus 4+ years of experience in CS, CE, ML, or related fields
• Hands-on experience developing and deploying VIO or visual-inertial SLAM systems
• Strong understanding of multi-sensor fusion and state estimation (EKF, factor graphs)