Computer Vision Engineer

Requirements

Must have:

- Strong Python experience for ML and inference workflows - Hands-on experience with PyTorch - Solid grounding in computer vision fundamentals (object detection, tracking, classification) - Experience deploying models into production environments - Practical experience with video processing frameworks (e.g. GStreamer, FFmpeg) - Experience optimising inference performance on GPU or edge platforms - Desirable Experience:

• Edge AI or embedded GPU platforms - Real-time or multi-stream video pipelines - TensorRT, ONNX, or similar optimisation toolchains - Linux-based development environments - Containerised ML or inference deployments - Experience balancing model accuracy vs. inference speed in constrained environments - Profile Sought:
• Engineer who remains hands-on with models and code - Comfortable working outside of pure research environments - Pragmatic problem-solver who understands production trade-offs - Enjoys debugging complex, real-world systems - Clear communicator who documents work effectively

Responsibilities:

- Own model deployment and optimisation in production environments - Work hands-on in real-time computer vision, optimising models and video pipelines - Collaborate closely with systems engineers to enhance performance and latency - Debug and resolve issues in complex, real-world systems

Company:

We are a specialist technology company near Cambridge dedicated to scaling a real-time AI platform. We are seeking Computer Vision Engineers who are passionate about model deployment and optimisation. In our team, you will have the opportunity to work on cutting-edge projects, with a focus on solving real-world problems. We value hands-on engineers who enjoy collaboration and clear communication.