Research Engineer/Scientist, Reinforcement Learning
We are building a general AI for robots that learns in the real world with minimal human supervision. Our robots collect massive amounts of data autonomously containing valuable failures and recoveries while minimizing unscalable human language advice and teleoperation. We develop world-model based reinforcement learning algorithms to learn reliable policies from this dataset and improve beyond human performance.
You might thrive in this role if you love developing cutting-edge reinforcement learning algorithms and are excited about applying them to real-world robotic systems at scale.
Responsibilities
- Develop and implement novel offline reinforcement learning algorithms
- Perform training of deep neural networks on large GPU clusters
- Collaborate with researchers in imitation learning and world models
Preferred Qualifications
- Deep technical knowledge and research experience in deep learning, reinforcement and/or imitation learning
- Experience implementing and debugging reinforcement learning algorithms
- Extensive experience in Python and at least one deep learning library such as JAX or PyTorch
- Publications in top conferences (e.g. NeurIPS, ICLR, ICML, CVPR, RSS, CoRL, ICRA)