Amazon
Applied & Research Scientist - Safe Autonomy Frontiers (SAF) Lab, Safe Autonomy Frontiers (SAF) Lab
$143K–$193K
Pasadena, CA · Full-time · Posted Oct 21, 2026
- Experience
- 3+ years with a Master’s degree, or a PhD; alternatively, PhD or equivalent research experience is stated.
- Education
- Master’s degree or PhD in computer science, robotics, control, mechanical engineering, electrical engineering, or a related field; or equivalent research experience.
About the job
Develop and validate safe autonomy methods for dynamic robots, from foundational research through hardware deployment and production-scale applications.
What you'll do
- Advance safe autonomy research, integrating control theory with learning and perception and validating methods on hardware.
- Test and validate robotic platforms, including locomotion, manipulation, and loco-manipulation.
- Publish research and collaborate with lab and production teams to bring robotics research into deployment.
What they ask for
- PhD or equivalent research experience; or a Master’s degree and 3+ years of applied science, research, or robotics engineering experience in a related field.
- Hands-on experience developing and deploying control algorithms and/or learning policies on physical robotic hardware.
- Working knowledge of safety-critical control, including control barrier functions and safety filters.
- Proficiency in C++ and Python; experience with robotics physics simulators; and demonstrated technical impact through shipped systems, patents, or top-tier publications.
Nice to have
- Experience with professional software development and taking robotics research from prototype to deployed product.
- Knowledge of learning-based robotics, control architectures, perception, or model-based control.
Pay
142,800.00 - 193,200.00 USD annually (base salary)
Tools
C++, Python, Isaac Gym/Sim, MuJoCo, PyBullet, control barrier functions, safety filters
AI focus
Research and apply safe reinforcement learning, learning policies, and layered safety filters integrated with perception and semantic reasoning for robotic autonomy.
Model-written summary · the original posting is authoritative