Computer Vision Engineer

The opportunity

The role

UUG.AI turns camera streams into useful, real-time signals for operations teams. As a Computer Vision Engineer, you will work across the model lifecycle: from framing a problem and preparing data to evaluating, deploying, and observing a model in production.

This is an engineering role for someone who enjoys making computer vision reliable outside a notebook. You will work with recordings from varied environments, constrained edge hardware, GPU-backed inference, and the product teams that turn model output into workflows people can trust.

Your impact

What you will work on

• Build and improve detection, segmentation, classification, and multi-object tracking pipelines.
• Define datasets, evaluation sets, and metrics that reflect the real operating conditions of customer deployments.
• Optimise inference for edge devices and GPU clusters without losing sight of accuracy, latency, and cost.
• Package and serve models through our production inference stack, including NVIDIA Triton where it fits.
• Investigate model failures using recordings, telemetry, and user feedback, then turn findings into measurable improvements.
• Collaborate with platform, workflow, and frontend engineers so model output is understandable and actionable.

About you

You may thrive here if

• You have hands-on experience building computer vision systems with Python and PyTorch or a comparable framework.
• You understand model evaluation and can explain why a metric or test set represents the problem being solved.
• You are comfortable with video, image processing, OpenCV, and the practical trade-offs of production inference.
• You can move between experiments and engineering work: tests, containers, APIs, profiling, and operational debugging.
• You communicate assumptions and results clearly and are comfortable owning a problem with support from the team.

You do not need to match every point. If the work sounds like a strong fit, tell us what you would bring and where you want to grow.

Useful additions

Helpful experience

• YOLO-family models, tracking algorithms, or segmentation workloads
• NVIDIA Triton, CUDA, TensorRT, or GPU performance profiling
• MLOps, dataset versioning, model monitoring, or automated evaluation
• Camera protocols, streaming media, or edge-computing environments
• Go or C++ alongside Python