Tech Stack

Description

You will develop algorithms for robotic embodied intelligence, focusing on building world models that enable robots to predict, plan, and generalize across complex physical tasks.

Requirements

• PhD in Machine Learning, Robotics, or related field (or Master's with 4+ years experience)
• Proficiency in Python and deep learning frameworks (PyTorch, JAX)
• Expertise in large foundation models (VLM, VLA)
• Strong understanding of world model architectures and action-conditioned generative modeling
• Requires 5 days/week in-office collaboration

Responsibilities

• Design and deploy vision-language-action models for contextual understanding and robot action policies
• Develop and train world models for action-conditioned prediction and long-horizon planning
• Research approaches to improve world model fidelity using multi-modal inputs
• Develop foundation models with spatial reasoning for high-precision robotic actions
• Integrate multi-modal data sources for natural human-robot communication