Atlas Research Engineer, SLAM & Spatial AI

Sourced from physicalai.jobs

• Design and implement real-time SLAM and perception-based state estimation for humanoid robots in unstructured, dynamic environments
• Build offline 3D reconstruction pipelines (multi-view geometry, SfM/MVS, neural reconstruction, depth/pose fusion) to generate geometric scene structure for VLM/VLA training
• Research integration of large VLA and VLM models with 3D spatial perception for semantic, language-grounded scene reasoning
• Bridge classical geometric methods and learned approaches, selecting optimization-based estimation versus learned representations
• Write high-quality, maintainable C++ and Python code within a large production codebase

• PhD in Robotics, Computer Vision, Machine Learning, Computer Science, or 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, and state estimation
• Experience with 3D reconstruction (SfM, MVS, multi-view geometry, neural/implicit reconstruction)
• Knowledge of probabilistic state estimation and sensor fusion (factor graphs, filtering, optimization on manifolds)
• Solid foundation in geometric perception math (Lie groups, nonlinear optimization, multi-view geometry)
• Strong analytical and debugging skills with reliable C++ and Python research code

• Experience with modern ML frameworks such as PyTorch and JAX
• Experience building reconstruction or data pipelines that produce training data for large vision or VLA models
• Familiarity with VLA / large behavior models and spatial grounding for manipulation
• Publications in top-tier venues (CVPR, ICCV, ECCV, RSS, ICRA, CoRL)