This is a fully remote position, open to applicants in Colombia, +2 more countries.

📋 Description

• Analyze and process large volumes of structured and unstructured data to identify patterns, trends, and opportunities for improving business processes.

• Design, develop, and validate statistical and Machine Learning models aimed at solving operational issues and generating measurable value for the organization.

• Implement and maintain reproducible and scalable data pipelines using Kedro, ensuring traceability and quality at every stage of the workflow.

• Build and evaluate time series models for forecasting and anomaly detection, selecting the most suitable methodology based on the context of the problem.

• Create clear visualizations and communicate findings to both technical and non-technical stakeholders, supporting data-driven decision-making.

• Collaborate with engineering and business teams to define success metrics, validation criteria, and deployment strategies for models in production.

⛳️ Requirements

• At least 3 years of experience in Data Science roles, with involvement in projects that implement models in production environments.

• Proficiency in Python for data analysis, statistical modeling, and developing Machine Learning solutions, including the use of scikit-learn and XGBoost.

• Experience in time series modeling (ARIMA, Prophet, ML-based models, or other approaches) applied to real business contexts.

• Knowledge in structuring data projects with Kedro and handling analysis and visualization libraries such as SciPy, Seaborn, and Matplotlib.

• Ability to rigorously evaluate, compare, and document models using appropriate metrics based on the type of problem (classification, regression, forecasting).

• Proficient in version control with Git and best software development practices applied to data science projects.