Senior Data Scientist - Remote Opportunity at Scanntech

About the Role

We are seeking a Senior Data Scientist to design, develop, and scale machine learning products based on large volumes of consumer data. This Senior Data Scientist remote position will focus on understanding shopper behavior, evaluating the outcomes of various actions through causal inference methods, transforming complex data into actionable insights, and overseeing the entire lifecycle of machine learning products, from exploration to customer impact.

What You'll Do

• Design and develop machine learning models applied to consumer behavior, experiments, and causal inference.
• Build explanatory and predictive models to understand key drivers of consumer behavior, identify habit changes, growing categories, coexistence patterns, and purchase decision drivers.
• Develop shopper segmentation models (purchase missions, consumption occasions, RFM, clusters, churn, loyalty, and switching behavior).
• Analyze the results of actions such as online and offline campaigns, promotions, launches, and their impact on various KPIs.
• Collaborate in designing and evaluating marketing and trade marketing actions.
• Work with large volumes of data at different levels of granularity (ticket level data, products, stores, time, customers, promotions, etc.).
• Lead the complete lifecycle of machine learning products: problem exploration and definition, feature engineering, modeling, productization, monitoring, and continuous improvement.
• Translate business needs into clear analytical questions and solid methodologies, and technical results into clear and actionable insights for non-technical stakeholders.

Requirements

• At least 2 years of experience in similar roles.
• Strong knowledge and experience in Python (pandas/polars, numpy, scikit-learn, etc.).
• Expertise in statistics and supervised and unsupervised machine learning.
• Experience working with large volumes of data (Big Data).
• Proficiency in SQL and working in distributed environments (Spark/PySpark preferred).
• Experience in feature engineering, model evaluation, and metrics.
• Knowledge of the lifecycle of production models (deployment, monitoring, retraining).
• Experience integrating models into data pipelines and/or analytical products.

Nice to Have

• Experience working in consumer goods and/or technology companies.
• Experience modeling consumer behavior, ideally with transactional data.
• Design of experiments, A/B testing, or other causal inference methods.
• Knowledge and/or experience in Big Data technologies within the Hadoop ecosystem (HDFS, Spark, Hive).
• Proficiency in R and bash.
• Experience with unsupervised models (clustering, PCA, embeddings, basket analysis, co-occurrences).
• Knowledge in econometrics and time series analysis.
• Evaluation of marketing and trade marketing actions.

What We Offer

• Excellent Organizational Climate: recognized by GPTW among the best companies to work for with a Culture for Innovation.
• Opportunities for growth and development.
• Internal training (Scanntech University).
• Free language training (English and Portuguese) during working hours.
• Integration with teams from various countries.
• Study days from the start and more than legally required.
• Part of the day off for birthdays.
• And much more!

Join Scanntech and make a difference! We value your attitude and desire to add value. Scanntech: Intelligence with Results.