Amazon
Applied Scientist, Navigation
$172K–$222K
San Francisco, CA · Full-time · Posted May 7, 2026
- Experience
- 2+ years of experience in robot navigation, motion planning, or autonomous systems.
- Education
- PhD in Robotics, Computer Science, Electrical Engineering, Controls, or a related field.
About the job
Leads research and deployment of robot navigation systems that combine learning-based planning with control-theoretic methods for safe operation in dynamic environments.
What you'll do
- Design and deploy robotics perception algorithms and lead research in computer vision, sensor fusion, and 3D perception.
- Own ML models end to end, from data collection and training through evaluation and deployment; track real-world performance.
- Collaborate across teams, mentor scientists and engineers, and publish research or contribute to patents.
What they ask for
- Programming experience in Java, C++, Python, or a related language.
- PhD in Robotics, Computer Science, Electrical Engineering, Controls, or a related field.
- Deep expertise in learning-based navigation approaches and strong experience with MPC and optimization-based planning using PyTorch, JAX, or equivalent.
- Track record of translating research into deployed systems.
Nice to have
- Experience applying foundation models or large pre-trained models to robotics tasks.
- Experience with sim-to-real transfer and high-fidelity simulation environments such as Isaac Sim, MuJoCo, or Gazebo.
Pay
171,600.00 - 222,200.00 USD annually (base salary)
Tools
Java, C++, Python, MPC, PyTorch, JAX, Isaac Sim, MuJoCo
AI focus
Develops learning-based robot navigation and planning, including potential use of foundation models for embodied agents; trains and deploys ML models on robots.
Model-written summary · the original posting is authoritative