About this role
UUG.AI turns camera streams into useful, real-time signals for operations teams. As a Computer Vision Engineer, you work across the model lifecycle: from framing a problem and preparing data to evaluating, deploying and observing models in production.
Your responsibilities
- Build and improve detection, segmentation, classification and multi-object tracking pipelines.
- Define datasets, evaluation sets and metrics reflecting real customer operating conditions.
- Optimise inference for edge devices and GPU clusters, balancing accuracy, latency and cost.
- Package and serve models through our inference stack, including NVIDIA Triton where appropriate.
- Investigate failures using recordings, telemetry and user feedback.
- Collaborate with platform, workflow and frontend engineers to make model output actionable.
This is a full-time engineering role, with hybrid collaboration from Ghent, Belgium.
- Hands-on experience building computer vision systems with Python and PyTorch or a comparable framework.
- Understanding of model evaluation and representative test sets.
- Comfortable with video, OpenCV, image processing and production-inference trade-offs.
- Able to work with tests, containers, APIs, profiling and operational debugging.
- Clear communication and ownership with support from the team.
Helpful, not all required: YOLO, tracking or segmentation; Triton, CUDA or TensorRT; MLOps, model monitoring and dataset versioning; camera protocols and edge computing; Go or C++. Relevant skills and practical experience matter; no mandatory diploma or fixed number of years.