Atlas Research Engineer, SLAM & Spatial AI

What you'll do

• Design and implement real-time SLAM and perception-based state estimation for humanoids or data-collection devices.
• Develop offline 3D reconstruction pipelines that produce geometric data for VLM/VLA training.
• Research spatial perception and integrate geometric methods with learned approaches for language-grounded scene reasoning.

What they ask for

• 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 at least one listed area: real-time SLAM and state estimation; 3D reconstruction; probabilistic state estimation and sensor fusion; or spatial representations and geometric foundation models.
• Strong mathematical foundation in geometric perception and ability to write reliable, well-structured C++ and Python code.

Nice to have

• Experience with PyTorch or JAX and how perception outputs feed large-scale model training.
• Experience building training-data reconstruction pipelines; familiarity with VLA/large behavior models; or publications at top-tier computer vision, ML, or robotics conferences.

Pay

$177,000 to $225,000 annually (base salary)

Tools

C++, Python, PyTorch, JAX, SLAM, SfM/MVS, VLM/VLA

AI focus

Research and develop spatial AI that grounds language and vision in 3D geometry, integrates VLM/VLA models with spatial perception, and produces geometric data for model training.