Senior Computer Vision Engineer - C++

About the Company

Kapdaa transforms UK garment waste into valuable recycled products. We are currently building AI4Fibres, an AI-powered textile recycling system which will run with UK textile waste.

Role Summary

You will build and own the real-time vision core of our sorting line: multiple synchronised camera streams per lane, GPU inference, and a per-item decision that must be made before the garment physically reaches the diverter. This is a deep engineering role on the hot path C++, concurrency, memory and GPU throughput where the target is not accuracy alone but accuracy delivered inside a fixed time budget, continuously, for a full shift. You will work to throughput and latency budgets and contribute to the architecture of the edge tier. This is a greenfield build on real hardware you will work on the line itself, with the cameras, lighting and conveyor, alongside the ML team whose models you deploy. The throughput you achieve is not just your result: it sets the rate the rest of the platform is designed around.

Key Responsibilities

• Image processing pipeline: own everything upstream of inference: intrinsic/extrinsic calibration and lens-distortion correction, homography from image space to the belt's encoder coordinate frame, flat-field and white/dark-reference correction, RGB↔hyperspectral spatial registration, background subtraction and connected-component/morphological segmentation to extract per-item ROI.
• Real-time C++ core: multi-camera capture and processing under a strict per-item latency budget: concurrency, thread and queue design, memory and buffer management, zero-copy where it counts.
• Multi-camera streaming: synchronized capture across cameras and lanes, frame timing and alignment, handling dropped frames and degraded sensors without stalling the pipeline.
• GPU inference integration: CUDA/TensorRT, model export and optimisation (ONNX, quantisation), batching, and keeping the GPU fed rather than stalled.
• Item identity & tracking: assign identity at detection and carry it through classification to routing, using spatial/encoder-based tracking rather than fragile timing windows.
• Performance engineering: profile, measure and defend: know where every millisecond goes, and produce numbers, not impressions.
• Edge deployment & operations: run reliably on GPU-backed edge devices (NVIDIA Jetson class) on the factory floor: startup, recovery, remote diagnostics, versioned rollouts, and behaving sensibly when something upstream fails.
• Vision pipeline quality: work with the ML team on model integration, and build the instrumentation that shows what the line is actually doing in production, not just what the model scored in training.
• Architecture contribution: shape the edge tier's design with the team and hold the interface contract between the vision core and the rest of the platform.