Atlas VLA Research Intern
Boston Dynamics
•
Waltham, MA
0
0
0
0
Not Applicable
Posted April 17, 2026
Job link
Thinking about this job
Responsibilities
Responsibilities
- Lead a high-stakes research project focused on either VLA scaling/training or spatial perception (SLAM/Calibration).
- Prototype and deploy your algorithms directly on Atlas, moving from simulation to hardware.
- Architect data pipelines that ingest alternative data sources to improve robot robustness.
- Write production-grade code (Python/C++) that integrates with our existing systems.
- Collaborate across teams To integrate learned policies with low-level robot control.
Not Met Priorities
What still needs stronger evidence
Requirements
- Lead a high-stakes research project focused on either VLA scaling/training or spatial perception (SLAM/Calibration).
- Prototype and deploy your algorithms directly on Atlas, moving from simulation to hardware.
- Write production-grade code (Python/C++) that integrates with our existing systems.
- Collaborate across teams To integrate learned policies with low-level robot control.
- Expertise in ONE or more of the following tracks:
- Training large-scale multimodal models (VLMs/LLMs), imitation learning, or generative world models for robotics.
- Classical and learned SLAM, visual odometry, or extrinsic/intrinsic camera calibration at scale.
- Experience troubleshooting and deploying algorithms on physical robot platforms, especially mobile and humanoid form factors.
- Experience working with and contributing to large-scale datasets (e.g., Open X-Embodiment) or specialized data collection approaches like Universal Manipulation Interface.
- Experience with large-scale cluster training (SLURM, distributed GPU training) and maintaining high-quality codebases.
- Strong grasp of Lie groups, optimization, or transformer architectures.
Preferred Skills
- Nice To Have
- Experience troubleshooting and deploying algorithms on physical robot platforms, especially mobile and humanoid form factors.
- Experience working with and contributing to large-scale datasets (e.g., Open X-Embodiment) or specialized data collection approaches like Universal Manipulation Interface.
- Experience with large-scale cluster training (SLURM, distributed GPU training) and maintaining high-quality codebases.
- Strong grasp of Lie groups, optimization, or transformer architectures.
Education
- (Not required) – Actively pursuing a PhD (preferred) or a research-heavy Master’s in Computer Science, Robotics, Machine Learning, or a related field.
Are you passionate about the intersection of foundation models and physical AI? As an intern on the Atlas VLA Research Team , you will join a world-class group of engineers and scientists dedicated to giving Atlas the intelligence to perceive, reason, and act.
Our team focuses on scaling Vision-Language-Action (VLA) models, leveraging diverse data sources, and building accurate spatial perception that keep Atlas grounded and capable of performing challenging dexterous tasks. We are looking for PhD-level interns to lead research projects that push the boundaries of what humanoid robots can do. You won't work on pure theory; you'll be deploying your ideas directly onto one of the most sophisticated pieces of hardware on the planet.
How You Will Make An Impact
Lead a high-stakes research project focused on either VLA scaling/training or spatial perception (SLAM/Calibration).
Prototype and deploy your algorithms directly on Atlas, moving from simulation to hardware.
Architect data pipelines that ingest alternative data sources to improve robot robustness.
Write production-grade code (Python/C++) that integrates with our existing systems.
Collaborate across teams To integrate learned policies with low-level robot control.
We Are Looking For
Actively pursuing a PhD (preferred) or a research-heavy Master’s in Computer Science, Robotics, Machine Learning, or a related field.
Expertise in ONE or more of the following tracks:
Training large-scale multimodal models (VLMs/LLMs), imitation learning, or generative world models for robotics.
Classical and learned SLAM, visual odometry, or extrinsic/intrinsic camera calibration at scale. Nice To Have
Experience troubleshooting and deploying algorithms on physical robot platforms, especially mobile and humanoid form factors.
Experience working with and contributing to large-scale datasets (e.g., Open X-Embodiment) or specialized data collection approaches like Universal Manipulation Interface.
Experience with large-scale cluster training (SLURM, distributed GPU training) and maintaining high-quality codebases.
Strong grasp of Lie groups, optimization, or transformer architectures.
The hourly pay range for this position is between $30-$45/ hour. Base pay will depend on multiple individualized factors including, but not limited to internal equity, job related knowledge, skills, education and experience. This range represents a good faith estimate of compensation at the time of posting.
Our team focuses on scaling Vision-Language-Action (VLA) models, leveraging diverse data sources, and building accurate spatial perception that keep Atlas grounded and capable of performing challenging dexterous tasks. We are looking for PhD-level interns to lead research projects that push the boundaries of what humanoid robots can do. You won't work on pure theory; you'll be deploying your ideas directly onto one of the most sophisticated pieces of hardware on the planet.
How You Will Make An Impact
Lead a high-stakes research project focused on either VLA scaling/training or spatial perception (SLAM/Calibration).
Prototype and deploy your algorithms directly on Atlas, moving from simulation to hardware.
Architect data pipelines that ingest alternative data sources to improve robot robustness.
Write production-grade code (Python/C++) that integrates with our existing systems.
Collaborate across teams To integrate learned policies with low-level robot control.
We Are Looking For
Actively pursuing a PhD (preferred) or a research-heavy Master’s in Computer Science, Robotics, Machine Learning, or a related field.
Expertise in ONE or more of the following tracks:
Training large-scale multimodal models (VLMs/LLMs), imitation learning, or generative world models for robotics.
Classical and learned SLAM, visual odometry, or extrinsic/intrinsic camera calibration at scale. Nice To Have
Experience troubleshooting and deploying algorithms on physical robot platforms, especially mobile and humanoid form factors.
Experience working with and contributing to large-scale datasets (e.g., Open X-Embodiment) or specialized data collection approaches like Universal Manipulation Interface.
Experience with large-scale cluster training (SLURM, distributed GPU training) and maintaining high-quality codebases.
Strong grasp of Lie groups, optimization, or transformer architectures.
The hourly pay range for this position is between $30-$45/ hour. Base pay will depend on multiple individualized factors including, but not limited to internal equity, job related knowledge, skills, education and experience. This range represents a good faith estimate of compensation at the time of posting.