Robotics Applied Scientist, Spatio-Temporal Scene Understanding & Memory

FieldAI • Irvine, CA

5d

About The Position

Investigate and develop representations for a robot’s persistent mission memory: a spatio-temporal account of what it observed, where and when it observed it, and how scenes changed across missions and sites. The memory should track assets that move, disappear, or degrade rather than requiring the robot to rediscover them. Build world models that enable reasoning and planning over this memory, and recover physical parameters through interaction to support physics-aware digital twins. Combine learned and physically grounded models, treating geometry and dynamics as ground truth, and bridge the perception-reasoning gap for long-term autonomy.

Requirements

• PhD in robotics, computer science, electrical engineering, aerospace engineering, mechanical engineering, or a related field.
• Publications at top venues such as RSS, CoRL, ICRA, IROS, T-FR, T-RO, CVPR, NeurIPS, or similar, on scene understanding, semantic SLAM, lifelong or spatio-temporal mapping, world models, or embodied reasoning.
• Hands-on experience applying vision-language or foundation models to spatial reasoning, memory, or long-horizon embodied question answering.
• Depth in 3D representations such as scene graphs, neural or Gaussian-splat maps, or object-centric maps, and the estimation methods underlying them.
• Strong Python skills.
• Ability to run methods on real robots using C++ and ROS 2.
• Clear thinking about the purpose of a representation and how to evaluate it.
• Comfort working in a fast-paced environment where research questions are shaped by deployment needs.

Nice To Haves

• Change detection or long-term mapping results from real deployments.
• Real2Sim, system identification through interaction, or digital-twin work.
• Experience with behavior trees or task planning driven by language models.
• Industrial or field robotics exposure.

Responsibilities

• Investigate appropriate representations for persistent spatio-temporal robot mission memory across missions and sites.
• Build world models that enable robots to reason and plan over mission memory.
• Recover physical parameters through interaction to support physics-aware digital twins.
• Combine learned and physically grounded models, using geometry and dynamics as ground truth.
• Bridge the perception-reasoning gap for long-term autonomy.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Ph.D. or professional degree