About this Applied Scientist - Learning-Based Navigation and Locomotion role at Rai
We aim to advance the mobility and autonomy of mobile robots to new heights by leveraging simulation based methods like Reinforcement Learning, augmenting them with model information.
Reinforcement Learning Applied Scientist will have proven hands-on research or industry experience focusing on one or more of these key areas: Learning-based navigation or locomotion, specifically end-to-end control methods from sensor data. Having practical hardware experience is essential for this role. If you are passionate about developing technology for robots and using it to advance their capabilities and usefulness, this team will be a great fit for you!
What you'll need
MS/PhD or equivalent industry experience in robotics, computer science, or related fields
2+ years of experience in research and development
Ability to demonstrate technical proficiency in Reinforcement Learning, Control, Robotics, or Imitation Learning
Experience with sim-to-real for robotic hardware specifically legged robots or highly dynamic mobile vehicles.
Experience in working with perception-based control
Advanced programming skills in Python or C++
Expertise with deep learning frameworks such as PyTorch and robotic simulation
Bonus
Experience in any of the following is a plus; none is required.
Knowledge of Model Predictive Control
Knowledge in robot perception
Experience in combining model-based and data-driven approaches
Experience in working with Isaac-Lab
Experience in working with ROS or ROS2
Experience with Docker, cloud computing, or similar applications
Experience with parallel programming (e.g., CUDA)
Proven track record in top-tier conferences and journals in Machine Learning, Robotics, Control, or related fields
These attributes are great to have but not required. Candidates who lack these should not be discouraged from applying.
