MARSS Group
Perception & Vision Systems Engineer
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
Perception & Autonomous Systems Engineer
Reports to: Head of Engineering
Location: Bristol
Type: Full time - permanent
Role Overview
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.
Reasons to use Rodeo
Start with a chat, not a search bar
Grad scheme, placement, apprenticeship? Not sure what you want yet — that's fine. Your agent talks it through with you and turns "I have no idea" into a shortlist.
It searches the market for you
Every day your agent scans the market matching roles against what actually matters to you, not just keywords on a CV.
Only hits
No noise. No "maybe this fits." Just roles with a clear explanation of why they're right — and where to focus when applying.
- 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.
Required Experience
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
Get help with your application
Your very own career expert that helps elevate your application to the next level.
Attributes & Mindset
- 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.
Working Environment
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.
We are committed to building an inclusive and diverse team where everyone is treated with respect and has the opportunity to contribute and succeed. We welcome applications from people of all backgrounds and are focused on creating a working environment where different perspectives, experiences and ideas are valued.
“It took my CV and asked me questions relevant to understanding what kind of jobs to suggest for me. Suggestions were almost perfect. Jobs were exactly what I’ve been looking for.”
Jessica, London
Skills
Location