VLA Research Scientist: Humanoid Manipulation

Boston Dynamics, Inc.; Waltham (MA); On-site; USD 100,000 - 130,000; Full time

Benefits offered by this job

Access to advanced humanoid robot

Collaborative team environment

Impactful applied VLA research

Job summary

Boston Dynamics, Inc. in Waltham, Massachusetts, is looking for a VLA Research Scientist to work on developing large-scale behavior models for the Atlas robot. You will focus on creating models that incorporate multimodal inputs to enhance dexterous manipulation capabilities.

The role involves collaborating with various teams to deploy and test models on actual hardware. The ideal candidate has a strong background in machine learning or robotics, with experience in training policies for complex robot behaviors. Enjoy direct access to cutting-edge robotic technology and a collaborative work environment focused on impactful applications.

Qualifications

• 3+ years of experience in machine learning or robotics.
• Prior experience training and deploying learned policies for complex robotic behaviors.
• Strong background in large-scale behavior models.

Responsibilities

• Architect and train end-to-end VLA and Large Behavior Models for mobile manipulation.
• Build large-scale imitation learning pipelines from diverse data sources.
• Develop policies for few-shot generalization across various tasks.

Skills

Behavior cloning / imitation learning

Multimodal learning (vision/language/action)

Strong analytical and debugging skills

Education

MS with 3+ years of experience or PhD in Machine Learning, Robotics, Computer Science

Tools

PyTorch

JAX

Python

C++

Job description

Boston Dynamics, Inc. in Waltham, Massachusetts, is looking for a VLA Research Scientist to work on developing large-scale behavior models for the Atlas robot. You will focus on creating models that incorporate multimodal inputs to enhance dexterous manipulation capabilities.

The role involves collaborating with various teams to deploy and test models on actual hardware. The ideal candidate has a strong background in machine learning or robotics, with experience in training policies for complex robot behaviors. Enjoy direct access to cutting-edge robotic technology and a collaborative work environment focused on impactful applications.