Data Scientist & LLM Engineer at UUG.AI
Full-time | Ghent, Belgium | Hybrid

Our platform produces a rich stream of recordings, detections, tracks, events, and operational context. Turn that data into dependable features and build language- and vision-language workflows that help users understand what happened.

You will combine product thinking with careful experimentation. The goal is not a clever demo: it is an evaluated, observable system that behaves predictably with real customer data and makes its uncertainty visible.

What you will work on
- Build vision-language and LLM workflows for summarisation, event understanding, search, and operational automation.
- Design evaluations, test sets, and feedback loops that measure quality, safety, latency, and cost.
- Explore event and media metadata to identify patterns that can become useful product capabilities.
- Develop retrieval and context strategies across structured data, model results, and selected media evidence.
- Productionise experiments as tested services or workflow stages with monitoring and clear failure behaviour.
- Work with product and engineering colleagues to scope problems, review output quality, and iterate from user feedback.

About you
- Strong Python skills and comfort with both data analysis and production software engineering.
- Practical experience with LLMs, vision-language models, retrieval, or adjacent applied-ML systems.
- An understanding of how to evaluate probabilistic systems beyond a few hand-picked examples.
- Able to work with structured and unstructured data and reason about provenance, access, and data quality.
- Clear communication of trade-offs and a preference for simple, testable approaches over unnecessary framework complexity.

Helpful experience
RAG, tool use, agent harnesses or structured-output workflows; multimodal models; MongoDB aggregation, vector search or large event datasets; evaluation tooling, observability and prompt versioning; media pipelines, computer vision or time-series analytics.

How we work
We value strong communication, disciplined and honest engineering, teamwork, and ownership. You do not need to match every point: tell us what you bring and where you want to grow.

Interested? Share your CV or profile and a short note about work that shows how you think. Apply via https://uug.ai/contact/ or contact Cedric Verstraeten through this listing.

Python, applied LLM or vision-language systems, model evaluation, and structured/unstructured data. Helpful: RAG, multimodal models, MongoDB, vector search, evaluation and observability tooling, media pipelines or computer vision.