Overview As an experienced Senior Applied Scientist, you will guide a small team to advance reinforcement learning for contact-rich manipulation on real robots. You'll shape the technical direction from simulation to hardware execution, ensuring robust, scalable policies that operate across Amazon's global robotics platform. You'll collaborate across control, perception, and hardware to deploy learned behaviors in real systems and contribute to the broader robotics community through publications. This is a mission-driven role focused on generalizable manipulation capabilities and rigorous scientific practice.
Compensation / Benefits- Medical, Dental, and Vision Coverage
- Maternity and Parental Leave Options
- Paid Time Off (PTO)
- 401(k) Plan
- RSUs and sign-on
- Health insurance and mental health support
Responsibilities- Set the technical direction for learning non-prehensile and contact-rich manipulation policies, from testing advances to hardware demonstrations
- Oversee RL approaches addressing diverse, demanding manipulation conditions
- Own the path from simulation training to reliable real-time execution on physical robots
- Demonstrate new manipulation capabilities on real robots at scale and convert results into repeatable methods
- Establish standards, evaluation practices, and data-informed improvement loops
- Mentor scientists and engineers and raise applied science rigor
- Collaborate with control, perception, and hardware to integrate learned behaviors into working systems
- Represent Amazon in academia through publications and talks
Key requirements- PhD or equivalent research experience
- 7+ years of applied research experience
- 3+ years building ML models for business applications
- Proficiency in Java, C++, Python or related language
- Track record training RL or imitation learning policies in simulation and transferring to physical systems
- 3+ years building and deploying learning-based control on robotic systems
- Experience leading technical projects and mentoring scientists or engineers
- mentoring
- leadership
- cross-functional collaboration
- reinforcement learning for robotics
- imitation learning
- sim-to-real transfer
