CrossTech
Senior Computer Vision Engineer
How your CV stacks up
Upload your CV to see how well it fits this job role
?%
CrossTech
CrossTech develops AI-powered infrastructure inspection and safety products for railways, highways and industrial assets. Our Intelligent Vision® platform turns video, imagery and LiDAR into actionable insight, helping operators detect risk earlier, prioritise maintenance and run safer, more efficient networks. Our systems operate in demanding, safety-conscious environments where reliability, speed and practical deployment matter as much as model accuracy. If you want to apply computer vision to real-world industries that make a difference to society CrossTech is for you.
The Opportunity
We are looking for a Senior Computer Vision Engineer who can own solutions beyond the notebook. You will design and improve computer vision models, build the surrounding software, integrate cameras and compute hardware, and take systems through site commissioning into reliable operation. You will work closely with the Head of Computer Vision, software engineers, product and delivery teams, and customer stakeholders to turn difficult operational problems into scalable products.
What success looks like: accurate, observable and maintainable computer vision systems that work continuously in the field - across changing light, weather, viewpoints, hardware constraints and imperfect data..
What you will do
- Own computer vision features end to end: problem framing, data strategy, prototyping, evaluation, optimisation, deployment, monitoring and iteration.
- Develop and productionise solutions for detection, classification, segmentation, tracking, anomaly detection and video analytics.
- Design and integrate complete vision systems spanning cameras, lenses, illumination, networking, sensors, edge compute and cloud services.
- Build robust real-time and batch pipelines for video, images, point clouds and metadata, including streaming, synchronisation and data-quality controls.
- Optimise inference for constrained or accelerated hardware, balancing accuracy, latency, throughput, power, reliability and cost.
- Create representative datasets and rigorous evaluation methods; diagnose domain shift, edge cases and false-positive/false-negative behaviour.
- Write readable, tested and documented Python and C++ code, contribute to architecture and code reviews, and improve engineering standards.
- Operate deployed systems with strong observability, reproducible releases and disciplined incident investigation and root-cause analysis.
- Mentor engineers, unblock complex technical work and communicate trade-offs clearly to technical and non-technical stakeholders.
- Work directly with customers and partners, translating operational needs and safety constraints into pragmatic technical decisions.
- Stay current with relevant research and tooling, selecting approaches on evidence and product value rather than novelty alone.
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.
What we are looking for
- +3 years professional experience building computer vision or robotics systems, including responsibility for production or field deployments.
- Strong practical knowledge of deep learning and classical vision, with hands-on experience using PyTorch or TensorFlow and OpenCV.
- Excellent Python skills (and strong working knowledge of C++ is very helpful); confidence developing on Linux in version-controlled, containerised environments.
- Proven experience integrating physical hardware such as industrial or network cameras, edge computers, GPUs, sensors or robotic platforms.
- Experience deploying real-time video or sensor-processing workloads and troubleshooting the full stack across software, drivers, networks and hardware.
- Sound understanding of camera geometry, calibration, image formation, video encoding/streaming and performance profiling.
- Experience with large, imperfect real-world datasets, including labelling strategy, data curation, experiment tracking and meaningful model evaluation.
- Strong software-engineering practice: modular design, testing, CI/CD, code review, documentation, reproducibility and operational monitoring.
- A structured, analytical approach to ambiguous problems and the judgement to make sensible trade-offs under delivery constraints.
- Clear written and verbal communication, collaborative working style and willingness to take ownership through to a dependable outcome.
- Ability and willingness to travel to deployment sites and undertake occasional planned out-of-hours work where operational access requires it. You may be required to go on the railway with the team to deploy and test systems from time to time.
Get help with your application
Your very own career expert that helps elevate your application to the next level.
Especially useful
- ROS/ROS 2, robotics, autonomous systems, remote operation or multi-sensor integration.
- GStreamer, FFmpeg, RTSP or other low-latency video pipelines.
- Point-cloud or 3D vision experience using LiDAR, PCL, depth sensors or photogrammetry.
- Model optimisation and deployment using NVIDIA GPU/Jetson, TensorRT, ONNX Runtime or comparable edge-acceleration platforms.
- Cloud ML and data pipelines on GCP, Azure or AWS, with Docker and production orchestration experience.
- MLOps practices including dataset/model versioning, automated evaluation, drift monitoring and safe rollout/rollback.
- Experience in rail, highways, construction, manufacturing or another regulated, safety-critical or operationally constrained industry.
- Technical leadership of projects or small teams, including mentoring and coordination across engineering disciplines.
- An MSc or PhD in computer vision, robotics, machine learning, computer science, engineering, physics, mathematics or a related discipline - or equivalent industry experience.
Interview Process
Introductory Call (30 minutes)
Discuss your background, motivations, and the role with a senior leader.
Technical Leadership Interview (1 hour)
Collaborate with technical leads (e.g., Lead Computer Vision, Head of Engineering, Lead Frontend) to explore your approach to technical strategy and collaboration.
Final Round Interviews (Single Session)
Leadership & Management Interview (45 mins)
Discuss your leadership philosophy, management experience, and soft skills with senior team members.
Team Fit & Values Interview (1 hour)
Meet engineering team members to assess collaboration and alignment with Crosstech’s values.
Timely feedback provided after each stage, with a designated team member as your main contact
“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