Field Ai

<div><a href="http://www.fieldai.com" rel="noopener noreferrer ugc" target="_blank">FieldAI</a>’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.</div>
<h2>What You Will Get To Do</h2><div>

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

</div>
<h2>What You Have</h2><div>

<li>
<p>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.</p>
</li>
<li>
<p>Research experience in active perception, informative path planning, vision-language models, or semantic mapping for exploration.</p>
</li>
<li>
<p>Hands-on work with vision-language or foundation models for robot perception, plus the physical principles governing them.</p>
</li>
<li>
<p>Fluency in Python and the ability to run your methods on real robots with C++ and ROS 2.</p>
</li>
<li>
<p>A principled fluency with uncertainty: Bayesian or information-theoretic planning, calibration, and conformal methods</p>
</li>

</div>
<h2>What Will Set You Apart</h2><div>

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

</div>

Robotics Applied Scientist, Active Perception

<div><a href="http://www.fieldai.com" rel="noopener noreferrer ugc" target="_blank">FieldAI</a>’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.</div>
<h2>What You Will Get To Do</h2><div>

<li>
<p>Develop inspection modalities beyond RGB, from sensing to insight, such as radiometric thermal, gas detection, and acoustic signatures.</p>
</li>
<li>
<p>Fuse these modalities into the perception and mission pipeline.</p>
</li>
<li>
<p>Implement sensing-based behavior activation.</p>
</li>
<li>
<p>Deliver per-asset evidence and alerts into the data platform and on-prem flows.</p>
</li>
<li>
<p>Analyze multimodal inspection performance across real-world deployments.</p>
</li>

</div>
<h2>What You Have</h2><div>

<li>
<p>MS in robotics, electrical engineering, mechanical engineering, aerospace engineering, computer science, or a related field, with 3+ years building sensing software for real robots.</p>
</li>
<li>
<p>Strong C++ and Python, and ROS 2 experience integrating sensor drivers and real-time pipelines.</p>
</li>
<li>
<p>Hands-on camera and thermal calibration, cross-modal registration, and the geometry to project detections between sensors and 3D.</p>
</li>
<li>
<p>Experience with real-time constraints: latency budgets, dropout handling, and persisting data through network outages.</p>
</li>
<li>
<p>A field mindset: you have debugged a sensor on a robot in a place with no desk.</p>
</li>

</div>
<h2>What Will Set You Apart</h2><div>

<li>
<p>Optical gas imaging, multi-gas sensing, or radiometric thermal analysis.</p>
</li>
<li>
<p>Acoustic anomaly detection for rotating machinery.</p>
</li>
<li>
<p>Predictive maintenance integrations (CMMS, SCADA) or functional safety experience.</p>
</li>
<li>
<p>Applying foundation models to thermal or non-RGB imagery.</p>
</li>

</div>

Robotics Software Engineer, Multimodal Inspection

<div><a href="http://www.fieldai.com" rel="noopener noreferrer ugc" target="_blank">FieldAI</a>’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.</div>
<h2>What You Will Get To Do</h2><div>

<li>
<p>Own the end-to-end inspection behavior success metric.</p>
</li>
<li>
<p>Build the evaluation loop: golden-labeled datasets, seeded-fault runs, and regression suites at feature, system, and release level that gate every release candidate.</p>
</li>
<li>
<p>Turn field evidence into training and evaluation sets.</p>
</li>
<li>
<p>Map technical performance to the metrics the customer measures.</p>
</li>
<li>
<p>Make failures legible: triage mission logs, attribute each miss to navigation, localization, perception, or behavior, and route it to the owning team with evidence.</p>
</li>

</div>
<h2>What You Have</h2><div>

<li>
<p>MS in computer science, robotics, aerospace engineering, or a related field, with 3+ years in robotics or ML engineering.</p>
</li>
<li>
<p>Strong Python, working C++, and comfort with ROS 2 logs, bags, and replay tooling.</p>
</li>
<li>
<p>Experience evaluating and fine-tuning vision or vision-language models (PyTorch, LoRA or similar), including building the datasets and metrics behind them.</p>
</li>
<li>
<p>Statistical rigor: knowing the difference between a benchmark number and a field result, and how to design an experiment that tells them apart.</p>
</li>
<li>
<p>Data pipeline skills to move evidence from robot to training set to dashboard.</p>
</li>

</div>
<h2>What Will Set You Apart</h2><div>

<li>
<p>Authored or maintained a robotics benchmark, evaluation suite, or challenge.</p>
</li>
<li>
<p>Simulation-based evaluation and sim-to-real validation.</p>
</li>
<li>
<p>MLOps for on-edge models: quantization, versioning, and rollout to a fleet.</p>
</li>
<li>
<p>Industrial inspection, gauge reading, or anomaly detection experience.</p>
</li>

</div>

Robotics Software Engineer, Mission Evaluation & Fine-Tuning

<div><a href="http://www.fieldai.com" rel="noopener noreferrer ugc" target="_blank">FieldAI</a>’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.</div>
<h2>What You Will Get To Do</h2><div>

<li>
<p>Investigate the appropriate representation for the robot's mission memory: a persistent spatio-temporal representation of what it saw, where, when, and how it changed, across missions and sites, so assets that move, disappear, or degrade are tracked rather than rediscovered.</p>
</li>
<li>
<p>Build world models that let the robot reason and plan over that memory and recover physical parameters through interaction for physics-aware digital twins.</p>
</li>
<li>
<p>Combine learned and physically grounded models, with geometry and dynamics as the ground truth.</p>
</li>
<li>
<p>Bridge the perception-reasoning gap for long-term autonomy.</p>
</li>

</div>
<h2>What You Have</h2><div>

<li>
<p>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, on scene understanding, semantic SLAM, lifelong or spatio-temporal mapping, world models, or embodied reasoning.</p>
</li>
<li>
<p>Hands-on experience with vision-language or foundation models applied to spatial reasoning, memory, or long-horizon embodied question answering.</p>
</li>
<li>
<p>Depth in 3D representations: scene graphs, neural or Gaussian-splat maps, or object-centric maps, and the estimation underneath them.</p>
</li>
<li>
<p>Strong Python; able to run your methods on real robots with C++ and ROS 2.</p>
</li>
<li>
<p>Clear thinking about what a representation is for and how to evaluate it, and comfort with a fast-paced environment where research questions are set by what the next deployment needs.</p>
</li>

</div>
<h2>What Will Set You Apart</h2><div>

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

</div>

Robotics Applied Scientist, Spatio-Temporal Scene Understanding & Memory

<div><a href="http://www.fieldai.com" rel="noopener noreferrer ugc" target="_blank">FieldAI</a>’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.</div>
<h2>What You Will Get To Do</h2><ul><li>Develop visual reasoning and inspection algorithm and pipeline for real-world deployments.</li>
<li>
<p>Build inspection and various robot behaviors as reusable primitives.</p>
</li>
<li>
<p>Integrate on-edge vision-language inference into the behavior loop under real compute and latency budgets.</p>
</li>
<li>
<p>Develop the robot's reasoning and judgment legible and integrate it across the mission workflow.</p>
</li></ul>
<h2>What You Have</h2><ul><li>MS in robotics, computer science, aerospace engineering, electrical engineering, or a related field, with 3+ years building software that runs on real robots.</li>
<li>
<p>Strong C++ and Python, and hands-on ROS 2 experience designing nodes and systems that ship.</p>
</li>
<li>
<p>Working knowledge of behavior trees and computer vision.</p>
</li>
<li>
<p>Experience integrating learned models into a robotics system.</p>
</li></ul>
<h2>What Will Set You Apart</h2><ul><li>Experience with open-vocabulary detection or visual grounding with VLMs on robots.</li>
<li>
<p>GPU inference optimization on embedded hardware (TensorRT, quantization, ONNX).</p>
</li>
<li>
<p>Thermal imaging or anomaly detection against reference imagery.</p>
</li>
<li>
<p>Deployments on legged platforms in industrial environments.</p>
</li></ul>

Field Ai

Open jobs at Field Ai

Robotics Applied Scientist, Active Perception

Robotics Software Engineer, Multimodal Inspection

Robotics Software Engineer, Mission Evaluation & Fine-Tuning

Robotics Applied Scientist, Spatio-Temporal Scene Understanding & Memory

Robotics Software Engineer, Vision-Language Reasoning & Behaviors

Working for Field Ai?

Featured companies