UK - Perception & Vision Systems Engineer - Autonomous Systems

We are seeking a specialist Perception & Vision Systems Engineer to lead the development of high-performance imaging pipelines for our interceptor drone’s seeker. This position focuses on the execution and optimisation of vision systems in real-time, high-stakes environments.

The role centers on the architecture of low-latency video pipelines-from MIPI/IP camera drivers through to CUDA-accelerated object detection and tracking. You will be responsible for ensuring our seeker can process high-resolution, high-FPS thermal and optical data, maintaining a stable and accurate state estimate that our guidance systems can rely on.

Key Responsibilities

• Vision Pipeline Architecture & Optimisation
• High-Throughput Processing: Design and optimise pipelines to handle large data packets (high-resolution video frames) at maximum FPS with minimal latency.
• Hardware Acceleration: Implement and tune vision algorithms using OpenCV, CUDA, and TensorRT to leverage the full power of NVIDIA Jetson edge hardware.
• GStreamer Experience: Build, debug, and maintain GStreamer pipelines for encoding, decoding, and frame manipulation across multiple camera modalities.
• Algorithm Development: Extend existing object detection and tracking systems, utilizing both deep learning and classical methods (e.g., ORB, SIFT, SURF) for robust target locking.

Sensor Integration & Hardware

• Camera Systems: Lead the integration of high-speed MIPI sensors, IP cameras, and
• Thermal (LWIR/MWIR) imaging systems.
• Driver Development: Troubleshoot and optimize camera drivers and V4L2 interfaces to ensure stable data acquisition under flight conditions.
• Coordinate Geometry: Manage spatial transformations and coordinate systems to bridge the gap between 2D image-space detections and 3D world-space tracking.

System Integration & Simulation

• ROS2 Integration: Maintain the perception-to-system interface via ROS2, ensuring vision outputs are efficiently consumed by the wider autonomous stack.
• Synthetic Data & Simulation: Utilize Unreal Engine, Unity, Gazebo or Other simulators to generate synthetic datasets and validate perception performance in virtual “edge case” scenarios.
• Testing & Validation: Implement rigorous unit and functional testing for perception modules, focusing on deterministic performance and edge-case reliability. Support field testing.

Industry Experience

• 3+ years in a specialised Vision Engineering or Perception role (UAV, Autonomous
• Vehicles, or Defence).
• 5-10 years professional engineering experience in C++ and Python, with a focus on
• real-time data processing.

Technical Expertise

• Edge Computing: Deep experience with the NVIDIA Jetson ecosystem (Orin/Xavier) and
• CUDA acceleration.
• Video Infrastructure: Expert-level knowledge of GStreamer, video codecs (H.264/H.265), and high-bandwidth image handling.
• Computer Vision: Proficiency in OpenCV and the deployment of models via TensorRT.
• Spatial Math: Comfortable with 3D geometry, coordinate transformations, and sensor calibration workflows.
• Embedded Linux: Comfortable working in Linux environments, including driver-level troubleshooting and system-level performance tuning.
• Git and Agile Methodologies

Preferred Skills

• Experience with Thermal/Infrared imaging and multi-spectral sensor fusion.
• Familiarity with classical feature extraction and matching (SURF, SIFT, ORB) for GPS-denied navigation or tracking.
• Hands-on experience with synthetic data generation pipelines (AirSim, Gazebo, or custom Unreal/Unity plugins).
• Understanding of IP-based vision protocols (RTSP/UDP) and low-level MIPI CSI-2 specifications.
• Object oriented programming.
• Full Driving License - willingness to travel to support testing and demos, * Data-Centric: You treat every frame as a critical packet of information where latency is the primary enemy.
• Hardware-Aware: You don’t just write code; you write code that understands the constraints and capabilities of the silicon it runs on.
• Iterative Prototyper: Comfortable in fast-paced R&D, moving quickly from a Python proof-of-concept to a highly optimised C++ production node.
• Rigorous Tester: Dedicated to functional safety, ensuring the seeker performs reliably in diverse lighting and thermal conditions.
• Comfortable working with multiple engineering disciplines in a small tight-knit team.
• Adaptable & Resilient: Stay calm and focused under pressure, maintaining a positive attitude that motivates others, adapting approach as challenges arise.

We believe in the value of working together in person and expect team members to be office-based for the majority of the working week. At the same time, we take a flexible pragmatic approach to working patterns, including start and finish times and remote working, to support a healthy work-life balance while meeting the needs of the team and project.