Perception Simulation Engineer II/III

We are looking for a Perception Simulation Engineer to build the sensor-simulation and synthetic-data backbone of our Unreal Engine simulation environment. This role focuses on making simulated perception good enough to develop and validate real perception and target-tracking software before flight, including high-fidelity RGB and thermal camera models, sensor feeds streamed onto ROS 2 topics, and synthetic data pipelines that feed our detection, tracking, and Target State Estimation stacks. You will work at the seam between Unreal Engine and perception pipelines, turning 'we can render a scene' into 'we can trust the perception numbers coming out of the sim.'

Responsibilities

• Synthetic Sensor Modeling (core of the role)
• Build high-fidelity RGB and long-wave IR (thermal) camera models in Unreal Engine, and render both views from platform-mounted cameras.
• Tune simulated camera output to match (or closely approximate) real-world camera performance — FOV, resolution, framerate, thermal response — driven by the specs of the sensors we actually fly (e.g. FLIR Boson / Boson+ LWIR).
• Implement realistic sensor noise, artifacts, motion blur, and failure modes so perception software is tested against hard cases, not clean renders.
• Support camera articulation independent of vehicle orientation (gimbal/boresight), so control-envelope requirements can be derived directly from camera specs.
• ROS 2 Integration
• Publish simulated camera imagery and sensor data onto ROS 2 topics using the shared strive_msgs / strive_interfaces contracts, so the same interface serves sim and hardware.
• Implement and test developer contracts and fulfill deterministic simulation requirements.
• Feed the perception pipeline and downstream Target State Estimation (TSE) with simulated sensor streams and ground-truth labels for evaluation.
• Synthetic Data & Target Simulation
• Build synthetic-data generation and export pipelines (imagery + bounding boxes / segmentation / range + pose ground truth) suitable for training and evaluating detection, tracking, and TSE models.
• Implement target injection: spawn and drive targets (vehicles, people, infrastructure) with configurable motion, including dynamic add/remove during a running mission to simulate delayed deployments and dynamic scenarios.
• Support target-hint / track integration based on ground based sensor tracking and ground-truth generation for scoring TSE accuracy (position/velocity/acceleration error).
• Asset & Scenario Pipeline
• Own the process to import external target CAD (e.g. TurboSquid) and Zone 5 platform CAD into the sim as usable, correctly-scaled models.
• Manage the 3D asset pipeline (models, materials, thermal material properties for the IR view).
• Enforce scenario-driven rules that need perception ground truth — e.g. inter-platform/target proximity and fratricide detection (position of each entity per timestep, squared-distance comparison against a scenario parameter for performance).
• Performance & Scale
• Optimize rendering for real-time and accelerated modes; build headless simulation modes for large-scale parallel scenario execution.
• Collaborate with the platform team to run perception sim in CI/CD for continuous evaluation of perception/TSE software.

Requirements

• Bachelor's in Computer Science, Computer Engineering, Robotics, Game Development, or related field — equivalent industry experience welcome.
• 3–6+ years developing in Unreal Engine with C++, including custom plugins/modules.
• Working knowledge of ROS 2 and integrating it with a simulation environment.
• Solid grounding in 3D graphics, real-time rendering, and camera/sensor models — projection, FOV, framerate, noise, and how they affect a downstream vision algorithm.
• Practical understanding of camera-based perception (detection/tracking) and what makes synthetic imagery useful (or useless) for developing it.
• Comfortable with software architecture, design patterns, and collaborative version-control workflows.

Nice to have

• Experience building sensor simulation for robotics/autonomous vehicles, especially thermal/IR or multi-modal (EO/IR/lidar/radar) sensing.
• Familiarity with synthetic data generation for ML perception (labels, sim-to-real gap, domain randomization).
• Knowledge of state estimation / multi-target tracking (Kalman/EKF, track-to-track association) enough to build meaningful TSE test scenarios.
• Experience with edge perception deployment (NVIDIA Jetson, TensorRT) and matching sim interfaces to on-target interfaces.
• Familiarity with UAV flight dynamics (JSBSim/PX4 SITL), gimbal/boresight modeling, and camera-on-platform geometry.
• GPU programming / compute shaders; procedural terrain or environment generation.
• Python for tooling and data-pipeline automation; Blueprint for rapid prototyping.
• 3D asset workflows (Blender/Maya) or photogrammetry; distributed/networked simulation.
• CI/CD for game-engine projects; deterministic / real-time simulation experience.

Benefits

• Competitive total compensation package
• Comprehensive benefit package options include medical, dental, vision, life, and more.
• 401k with company-match
• 4 weeks of paid time off each year
• 12 annual company holidays