Perception Simulation Engineer II/III

Remotefull timeRemote

Apply on Employer Site

mid

$145k–$175k

H1B: no

Zone5 Technologies Perception Simulation Engineer II/III at Zone5 Technologies builds high-fidelity sensor simulations in Unreal Engine to validate perception and target-tracking software before flight. The role focuses on synthetic sensor modeling, ROS 2 integration, and synthetic data pipelines for detection and tracking models.

Responsibilities

We welcome both generalists and specialists—you do not need every skill listed below.
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.

Qualification

Bachelor's in Computer ScienceSolid grounding in 3D graphicsComfortable with software architectureGPU programming / compute shaders

Required

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.

Preferred

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.