Atlas Research Engineer, SLAM & Spatial AI
Boston Dynamics6 days ago
Waltham, MA, USAEntry Level
Base Salary
$177k - $225k/yr
Responsibilities
- Design and implement real-time SLAM and perception-based state estimation for mobile humanoids and data-collection devices.
- Build offline 3D reconstruction pipelines from teleoperation and robot logs using multi-view geometry, SfM/MVS, neural reconstruction, and depth/pose fusion.
- Integrate VLA and VLM models with 3D spatial perception for semantic, language-grounded scene reasoning.
- Combine optimization-based geometric estimation with learned representations for spatial AI research.
- Write maintainable, reliable C++ and Python code for a large production codebase.
- Test perception and reconstruction systems rapidly on humanoid hardware and collaborate with robotics, perception, ML, and systems teams.
Requirements
- PhD in Robotics, Computer Vision, Machine Learning, Computer Science, or a related field, or equivalent experience.
- Prior experience building and deploying SLAM, visual odometry, or 3D reconstruction systems for robots or autonomous vehicles.
- Strong background in real-time SLAM, visual-inertial odometry, state estimation, 3D reconstruction, probabilistic state estimation, sensor fusion, spatial representations, or geometric foundation models.
- Strong understanding of Lie groups, nonlinear optimization, and multi-view geometry.
- Ability to write reliable, well-structured research code in C++ and Python, with strong analytical and debugging skills.
- Preferred experience with PyTorch or JAX and with perception, reconstruction, or data pipelines that produce training data for large vision or VLA models.
- Preferred familiarity with VLA or large behavior models and publications in leading computer vision, machine learning, or robotics conferences.
Benefits
- Medical, dental, and vision benefits.
- 401(k), paid time off, and an annual bonus structure.
- Direct access to advanced humanoid robot hardware for frequent testing.
- Collaborative, inclusive, mission-focused environment focused on applied spatial perception and VLA research.