Computer Vision Engineer

UUG.AI; Oost-Vlaanderen; Hybride; EUR 60 000 - 90 000; Plein temps

Résumé du poste

UUG.AI is seeking a Computer Vision Engineer to build and optimize CV systems for edge devices and GPU clusters. You will handle the full model lifecycle from problem framing to deployment and monitoring in production.

You will work with varied data, constrained edge hardware, and a production inference stack, collaborating with platform and frontend engineers to ensure usable model outputs.

Qualifications

• Hands-on experience building computer vision systems with Python and PyTorch or a comparable framework.

Responsabilités

• Build and improve detection, segmentation, classification, and multi-object tracking pipelines.

Connaissances

Python

PyTorch

OpenCV

Go

C++

Outils

NVIDIA Triton

CUDA

TensorRT

Description du poste

Train, optimise, and ship detection, tracking, and classification models that run on edge devices and GPU clusters.

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.

Useful additions

Helpful experience

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

How we work

Skills differ by role. These are the behaviours we expect from everyone building UUG.AI.

• 01

  Strong communication

  Share context, decisions, and concerns clearly. Ask questions early, listen carefully, and adapt the message to the people involved.

• 02

  Disciplined and honest

  Do what you say, work with care, and be direct about uncertainty or mistakes. We value evidence and transparency over appearances.

• 03

  Team player and owner

  Help the team succeed while taking responsibility for the outcome. Collaborate openly, follow through, and leave the work better than you found it.

A clear start

What to expect in your first months

The exact pace depends on the role and your experience. We use these steps to align on support, ownership, and useful outcomes.

• 01

  Learn the operating context

  Start by running existing pipelines, reviewing representative recordings, and learning how model output moves through the platform.

• 02

  Own a measurable improvement

  Take on a bounded model or performance problem, agree on the evaluation criteria, and ship an improvement with the team.

• 03

  Grow end-to-end ownership

  Progress toward taking a vision capability from problem definition through deployment, monitoring, and iteration.

How we hire

A practical conversation, both ways.

We want you to understand the work, the team, and our expectations before making a decision.