Senior Perception Engineer

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.

• Design, build, and deploy perception systems for autonomous robots operating in complex real-world environments
  , taking ownership from initial design through on-robot deployment and long-term maintenance.
• Develop new perception capabilities by leveraging existing model outputs where possible and designing new algorithms or perception tasks where needed.
• Work extensively with LiDAR and vision data
  , with a strong emphasis on 3D perception and geometric reasoning as core components of the perception stack.
• Develop and integrate multi-sensor perception algorithms
  , combining information across sensors to provide robust and reliable outputs in both simulation and real-world deployments.
• Partner closely with planning and autonomy teams to define perception outputs that directly support downstream decision-making, navigation, and safety.
• Debug perception and system-level issues in the field
  , including sensor timestamps, synchronization, calibration, data quality, coordinate frames, and hardware/software integration. Determine whether issues should be solved within perception or addressed upstream with the core platform team.
• Bring algorithms all the way to physical robots
  , profiling, debugging, and optimizing them under real compute, latency, sensor, and environmental constraints.
• Continuously evaluate and improve perception performance through offline evaluation, simulation, on-robot testing, and field validation.
• Solve long-tail and safety-critical perception challenges by developing scalable data mining, training, and evaluation pipelines for rare real-world scenarios.
• Ensure model quality across releases by developing evaluation methodologies, regression detection systems, and practical performance metrics—including ground-truth-free metrics where appropriate.
• Improve the robustness, scalability, and maintainability of the perception stack
  , balancing rapid product development with long-term system quality.

• Bachelor’s degree in Computer Science, Robotics, Machine Learning, or a related technical field;
  graduate degree preferred
  .
• 4+ years of professional experience in machine learning, computer vision, robotics, or related areas, with substantial hands‑on perception engineering experience.
• Hands‑on experience deploying perception systems on real‑world robotic platforms
  ; experience limited to simulation or offline datasets is not sufficient.
• Strong experience working with LiDAR and vision sensors
  , particularly for 3D perception and real‑world robotics applications.
• Strong systems‑level understanding of perception and its interaction with the broader autonomy stack, with the ability to reason about interfaces, latency, failure modes, and downstream behavior.
• Experience with planning, navigation, or controls is a strong plus
  , especially where perception outputs directly influence robot behavior.
• Experience debugging systems
  , including sensor data quality, synchronization, calibration, coordinate transforms, and failures observed only during real‑world operation.
• Ability to own complex perception subsystems end‑to‑end
  —from technical design and implementation through deployment, validation, debugging, and long‑term maintenance.
• Strong software engineering fundamentals and experience writing robust, production‑quality C++.
• Experience with CUDA and GPU optimization is highly desirable.
• Background in autonomous vehicles, field robotics, mobile robotics, or similarly complex real‑world autonomous systems.
• Ability…