Applied Data Scientist

Do you have experience in Python?, * A strong applied ML background, comfortable across both classic ML and transformer models.

• Hands-on with the stack: Python, PyTorch, scikit-learn, HuggingFace, Pandas, MLflow, Databricks, Snowflake.
• Rigorous about evaluation, you ship models that survive contact with production, not just the notebook.
• A communicator and co-creator: strong IC who thinks, shares, and explains ML in plain business language (data-driven storytelling and visualization a real plus).
• Nice to have: financial/accounting domain exposure and experience with large document corpora.
• Fluent English is a must.

• Personal development: A generous training budget available from day one for specialised certifications, courses and training to solidify your expertise.
• Time off and flexibility: Plenty vacation days (and the option to buy extra days), plus the possibility of Workation: up to 5 weeks per year of remote work.
• Well-being & focus: Access to lifestyle coaches, well-being programs and other initiatives that contribute to your well-being and focus.
• Financial security: A competitive base salary with attractive benefits.
• Plenty of opportunities : Enjoy the speed and autonomy of an innovative scale-up, backed by the stability, vast resources, and global career network of the Visma Group
• Team & international culture: Participate in (international) team-building days, and other Yuki events that strengthen the close team spirit in a diverse and international environment.

Hi there, welcome to Yuki! As a vibrant, international IT scale-up, we support accountants, businesses, and entrepreneurs in handling their accounting more efficiently, simply, and enjoyably. And to make that possible? Well, we’re looking for kick-ass colleagues to complete our ambitious, cheerful, and lively team of top professionals!

Come on, now: that sounds like something for you, right?!

A True Yukiaan at Heart

Driven, enthusiastic, and with a quirky side: there’s always some buzz in our trendy office in Berchem. And that’s the way we like it! We’re eager to achieve results, take on our responsibilities, support each other through thick and thin, and continuously focus on an innovative future.

Everything can be improved, and… you can definitely contribute to that!

Values Worth Having

At Yuki, we place our employees first and foremost. Togetherness, authenticity, and collective momentum: that’s what we’re all about, day in and day out! We consciously choose colleagues who align closely with our core values:

• Entrepreneurial - Dare, do, and persist. At Yuki, we continuously encourage innovation, self-development, and initiative.
• Responsible - We are all essential links within Yuki, and we are aware of our responsibilities.
• Dedicated - Involved, helpful, and full of passion: as one close-knit team, we always go the extra mile.
• Inclusive - We all embrace each other’s diversity within an equitable, flat company structure.

Well, enough about us: it’s high time to talk about your role in our organization! Let’s go!

Your Role at Yuki

As our Applied Data Scientist, your mission is to build the machine-learning models that make Yuki smart - the models that classify documents and predict the right general ledger (grootboek), turning a client’s raw invoices into clean, usable accounting data.

This is a modeling role with real production discipline. You won’t just train models and walk away; you’ll keep them accurate as the data and the business shift. And you won’t be heads-down in isolation either. You’ll co-create with engineers and product people, and you’ll grow a genuine understanding of how accountants actually think about a document.

• Build the models: Train and evaluate classic ML (XGBoost, scikit-learn) and transformer models for document classification and ledger prediction.
• Fine-tune LLMs: Do real model training and fine-tuning with PyTorch and HuggingFace
• Design experiments: Own feature engineering, model evaluation, and selection, plus embedding and retrieval strategy for vector search.
• Guard production quality: Run drift detection, eval pipelines, and the MLflow model registry so models hold up over time.
• Learn the domain: Build deep understanding of accounting and financial-document structure, and translate it back into modeling decisions.