Robotics Applied Scientist, Active Perception

FieldAI’s Irvine team is where embodied AI meets real robots, real sensors, and real field deployments. Based in the heart of Southern California’s robotics ecosystem, we build risk-aware, reliable, field-ready AI systems that solve the hardest problems in robotics and unlock the full potential of embodied intelligence. If you want your work to ship, get tested on hardware, and improve through real deployments, Irvine is the place. We go beyond typical data-driven approaches or pure transformer-only architectures, combining rigorous engineering with learning systems proven in globally deployed solutions that deliver results today and get better every time our robots run in the field.

Formulate the active perception problem for inspection and a broad range of robot behaviors Develop viewpoint planning policies for active information gathering Research calibrated confidence and abstention for vision-language reasoning on the robot Own the research and development work through to the real-world experiments that prove feasibility and deployability Investigate and shape the technical roadmap, aligning real-world needs with technical development Mentor junior team members and collaborators

PhD in robotics, computer science, electrical engineering, aerospace engineering, mechanical engineering, or a related field, with publications at top venues such as RSS, CoRL, ICRA, IROS, T-FR, T-RO, CVPR, NeurIPS, or similar. Research experience in active perception, informative path planning, vision-language models, or semantic mapping for exploration. Hands-on work with vision-language or foundation models for robot perception, plus the physical principles governing them. Fluency in Python and the ability to run your methods on real robots with C++ and ROS 2. A principled fluency with uncertainty: Bayesian or information-theoretic planning, calibration, and conformal methods

Real-robot experience in the wild Work on metric-semantic scene graphs, open-vocabulary mapping, or spatio-temporal scene representations. Experience fine-tuning or deploying compact VLMs on edge computers Exposure to robotic industrial inspection workflows