AI Research Engineer/Scientist - Human Data - Robotics

What you'll do

• Build capture pipelines that integrate human demonstrations and wearable data into foundation-model and reinforcement-learning workflows.
• Reconstruct 3D objects and environments from capture data and use them in simulation for scenario synthesis.
• Develop and evaluate multimodal robot policies, reinforcement-learning systems, and algorithms for transferring human actions to robotic platforms.

What they ask for

• PhD in Computer Science, a related field, or equivalent practical experience.
• Experience with vision, vision-language, video, and other multimodal models, especially those trained with human data.
• Experience with multimodal generative modeling, training, and inference.
• Experience with reinforcement learning and imitation learning.

Nice to have

• Experience with capture methodologies, dataset design, and incorporating captured human action data into VLA, WAM, or RL training.
• Experience with simulators and real-world robots, especially dexterous manipulation and multimodal sensing.

Tools

UMI, reinforcement learning, imitation learning, VLA, WAM, tactile, forces

AI focus

Builds and evaluates robotics foundation models and multimodal policies using human action data, generative modeling, reinforcement learning, and imitation learning.