Junior Data Scientist

Responsible for developing and implementing analytical and machine learning models that optimize the investment and performance of Marketing Performance acquisition channels, working with the support and mentorship of the HQ Data Science team. This is an accelerated growth position, designed to consolidate the occupant as a full Data Scientist within a 2 to 3-year horizon.

MAIN RESPONSIBILITIES

• Design and develop statistical and machine learning models (linear/logistic regressions, classification models, time series) applied to attribution, demand forecasting, and media optimization.
• Explore and prototype neural network models for marketing use cases (lead scoring, purchase propensity, advanced segmentation), with technical support from the HQ Data Science team.
• Build data pipelines and feature engineering to feed the models, in collaboration with the local data team.
• Validate, document, and monitor model performance in production (drift, accuracy, recalibration).
• Translate complex analytical results into actionable recommendations for the Marketing Performance team and leadership.
• Collaborate directly with senior Data Scientists at HQ to adopt best practices, frameworks, and global team standards.
• Contribute to the development of an advanced analytics roadmap for the acquisition area.

REQUIREMENTS

Education

• Full Bachelor's degree in Data Science, Actuarial Science, Engineering, Mathematics, Statistics, Physics, Quantitative Economics, or related fields.
• Desirable (not exclusionary): postgraduate studies or specialized certifications in Data Science / Machine Learning.

Experience

• 4–6 years of experience in data analytics, with at least 1–2 years working on statistical or machine learning models.
• Previous experience in marketing, e-commerce, digital media, or commercial areas is a plus.

Technical Knowledge

• Python (pandas, scikit-learn, numpy) at an intermediate-advanced level for modeling and analysis.
• Solid statistical understanding: linear and logistic regressions, hypothesis testing, time series.
• Conceptual knowledge of neural networks and deep learning (basic architectures, use cases, frameworks like TensorFlow/PyTorch), without requiring expert proficiency — development is expected with HQ support.
• Advanced SQL for extraction and manipulation of large data volumes.
• Power BI / Power Query for visualization and communication of results to the business.
• Desirable: experience with cloud platforms (Azure, AWS, or GCP) and MLOps tools.