Senior Data Scientist (ML and Fraud Detection)

Scalo is a company delivering software projects and supporting partners in business development. They create software that enables people to make changes, act faster, and achieve better results. Their fields of activity include technology consulting, software development, embedded systems, cloud solutions, data management, and dedicated project teams.

• Experience as a Data Scientist on projects involving Machine Learning.
• Strong knowledge of Exploratory Data Analysis (EDA) and the ability to derive insights from large, complex, and unstructured datasets.
• Practical experience in feature engineering, especially in identifying predictive signals.
• Experience working with highly imbalanced, missing, or degraded data.
• Experience in fraud detection.
• Strong knowledge of tree-based algorithms, particularly XGBoost.
• Proficiency in Python and its Data Science libraries.
• Ability to independently define, conduct, and analyze experiments.
• Ability to work with requirements and translate them into analytical actions.
• Skills in data visualization and reporting.
• Strong documentation skills and knowledge sharing.
• Experience with Machine Learning solutions in the AWS environment.
• English language proficiency at C1 level for daily communication.

Nice to have:

• Practical knowledge of Amazon SageMaker.
• Experience in aviation, travel, payment services, financial services, or fraud prevention industries.
• Knowledge of MLOps practices and production Machine Learning environments.
• Experience presenting results to technical and non-technical teams.
• Experience mentoring and promoting good Data Science practices.

• Developing and improving fraud detection models for the aviation industry.
• Conducting analyses on large, complex, and imperfect datasets to identify patterns and anomalies.
• Designing, conducting, and evaluating experiments to validate hypotheses and improve model quality.
• Utilizing Python, SQL, AWS, Amazon SageMaker, XGBoost, Scikit-Learn, Pandas, and NumPy.
• Designing advanced feature engineering methods to enhance predictive value.
• Building, evaluating, and optimizing Machine Learning models, particularly tree-based algorithms like XGBoost.
• Handling highly imbalanced data, missing data, and degraded features.
• Documenting analyses, experiments, methodologies, and recommendations, emphasizing reproducibility and notebook work.

100% remote service delivery mode.