Machine Learning Intern, Manipulation

About the role

Persona AI is seeking a Machine Learning Intern to contribute to the development of machine learning models and infrastructure for our humanoid robots. This role involves solving real-world challenges in robotics, particularly focusing on manipulation tasks. You will join a team dedicated to creating reliable, large-scale robotic products.

Key facts

What you'll do

• Develop and enhance machine learning models and their supporting infrastructure with the ML team.
• Track and assess the real-world performance of deployed models.
• Contribute to the design and creation of Persona's ML software stack, applying it across manipulation, navigation, locomotion, and perception.

Requirements

• Experience with deep learning frameworks.
• Experience with cloud computing for model development and data management.
• Solid grasp of current research in robot learning, including behavior cloning, reinforcement learning for manipulation, and world models.
• Awareness of the difficulties involved in deploying neural network models in physical environments.
• Ability to produce high-quality software.
• Eagerness to collaborate within a fast-paced team setting.
• Strong first principles thinking.

Nice to have

• Master's or PhD degree in computer science, robotics, machine learning, or a related discipline.
• Publications in leading ML or Robotics conferences (ICML, ICRA, CoRL, RSS, NeurIPS).

Skills & tools

• PyTorch
• JAX
• TensorFlow
• AWS
• Azure
• GCP

Practical notes

• This is an onsite position in Houston, TX.