Senior Data Scientist

We - Cafeyn Group

With 15 years of existence, Cafeyn Group is a multi-brand company composed of Cafeyn, Blendle, MiLibris and KidJo and based in France, Netherlands, UK, Canada and Morocco. With almost 140 employees, we propose a media experience through different products. We want to achieve strong business performance across the Cafeyn Group through organic growth, diversified revenue streams and sustainable profitability. New opportunities are continuously sought by investment both within and outside of the business. We deliver high-value, high-focus and forward-thinking, premium infotainment (information & entertainment content) services to our partners and customers, with personalised and relevant information to entertain and educate our audience, broadening their perspective and making them more knowledgeable.

Your responsibilities

As a Data Scientist, you’ll be part of the awesome Data team, which consists of Data Scientists, Data Analysts, Data Engineers, and BI Engineers. You’ll work closely with this data team and the Product team to envision, develop, and optimize features benefiting the Cafeyn product.

The Data Science playfield

Data Science at Cafeyn powers product features for recommendations and personalization, aiming to boost user satisfaction and engagement by delivering the right content at the right time. It handles pipelines, models, and algorithms to analyze content from publishers and user interactions, and develops systems for personalized recommendations and search.

Your missions

Broadly speaking Data Science has 3 three working areas that are covered by members of the team.

• Machine Learning/AI - Training, tuning and applying predictive models

• Analytics and Statistics - Analyzing large-scale behavioral data, and designing, analyzing, and executing experiments.

• Engineering - Designing and building data applications and services

As a Data Scientist, you will specifically be working on:

Analyzing User Behavior and Interaction

• Gather actionable insights into content preferences across different times of the day and week.

• Understand how users explore and discover content to refine recommendation strategies.

Designing, Implementing, and Analyzing Experiments

• Conduct experiments to improve metrics like recommendation adoption rates and content-driven newsletter click-through rates.

• Apply advanced testing methods such as multi-armed bandit algorithms and Bayesian optimization for effective experimentation.

Optimizing and Tuning ML/AI Models

• Focus on training, retraining, and fine-tuning models to maximize performance for specific tasks.

• Enhance capabilities like article topic classification and geographic location identification in content.

Your must-have skills and education

• MSc or comparable degree in Data Science, Computer Science, Computational Linguistics, or an adjacent field.

• At least 4 years’ experience as a Data Scientist, Machine Learning Engineer or similar role, and at least 2 years’ working with NLP technologies (text representation, semantic extraction techniques, data structures and modeling) and/or Large Language Models

• Well-organized and a self-starter, having the ability to work independently

• Basic proficiency in Python

• Ability to understand technical documentation and research papers to keep up with the state of the art in Machine Learning and Natural Language Processing