Perception Engineer, Autonomy (Air Domain)

Applied Intuition•Fort Walton Beach, FL

1d•Onsite

About The Position

Applied Intuition is hiring a Perception Engineer to build the perception layer of an autonomy stack for uncrewed air vehicles. The team combines noisy, intermittent data from multiple sensors and teammates to produce a reliable picture of the airspace. The role spans classical state estimation and tracking, sensor fusion, and learning-based prediction, including models that increasingly adapt online during an engagement from limited and delayed feedback. The engineer will design and implement real-time C++ algorithms, build tooling and simulation studies to evaluate them, and bring research prototypes into deployable software. The role requires fluency in estimation theory and machine learning, rigorous measurement of results, and comfort working between research and production. The work includes sensor interfacing and control, collaboration across sensor, tracking, and autonomy teams, deployment to embedded Linux devices, and interaction with Department of Defense customers during field events. Applied Intuition is an in-office company. Full-time employees are expected to primarily work from an Applied Intuition office five days a week, with occasional remote work and schedule flexibility. This expectation does not apply to contractor positions.

Requirements

Bachelor's or master's degree in Electrical, Aerospace, or Mechanical Engineering, Computer Science, Robotics, or a related field, plus 3+ years building perception or estimation software for autonomous systems.
Strong modern C++ (17/20) for real-time, performance-critical code on Linux.
Familiarity with linear algebra libraries such as Eigen and profiling.
Grounding in state estimation, including Kalman filter variants (EKF/UKF), multiple-model filters (IMM), and covariance and uncertainty handling.
Experience with multi-target tracking and sensor fusion, including data association, track management, and fusion of heterogeneous sensors with intermittent, noisy reports.
Working knowledge of machine learning for prediction, including sequence models (RNN/LSTM, transformers), training pipelines, and evaluation on held-out data.
Python skills for data pipelines, analysis, and visualization of logged and simulated runs.
Experience validating algorithms in simulation and with recorded data, including experiment design, metric definition, and objective interpretation of results.
Bachelor's degree in Computer Vision, Computer Science, Electrical Engineering, Robotics, or a related technical field.
2+ years of industry experience.
Must be a U.S. citizen.
Must hold or be eligible to obtain and maintain a U.S. security clearance.

Nice To Haves

Experience with online, real-time learning, including models that adapt during operation rather than only through offline training.
Background in adaptive control or learning-based estimation, such as concurrent learning, Lyapunov-based learning, or Bayesian or recursive least-squares parameter estimation.
Experience learning from intermittent, delayed, or sparse feedback where ground truth arrives late or only occasionally.
Experience with behavior and intent prediction for other agents, including non-cooperative or adversarial actors.
Experience deploying small neural networks in C++ without heavy ML frameworks under tight latency and compute budgets.

Responsibilities

Develop, integrate, and adapt AI/ML algorithms for the perception autonomy stack to collect relevant information across platform sensors.
Create interfacing software to autonomously control sensors, including EO, IR, acoustics, radar, and RF.
Collaborate with sensor, tracking, and autonomy teams to support deployment of heterogeneous platform swarms in on-site DoD testing and demonstration events.
Deploy containerized solutions to embedded Linux devices, using computer-in-the-loop testing and profiling and collecting performance data.
Work with DoD customers to understand use cases, requirements, and triage needs during field events.