Atlas VLA Research Intern at Boston Dynamics in Waltham, MA

Summary: Boston Dynamics is a company focused on advancing physical AI through innovative robotics. As an intern on the Atlas VLA Research Team, you will lead research projects in Vision-Language-Action models and spatial perception, deploying your ideas on sophisticated robotic hardware. 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 Required Qualifications: - Actively pursuing a PhD 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 - Expertise in ONE or more of the following tracks: Classical and learned SLAM, visual odometry, or extrinsic/intrinsic camera calibration at scale Preferred Qualifications: - 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 Required Skills: Python, C++, VLA scaling/training Important Skills: SLAM, Machine Learning, Robotics Nice-to-Have Skills: Large-scale datasets, Distributed GPU training, Optimization, Transformer architectures