Capgemini

Senior Data Scientist

Capgemini Bogota, RAP (Especial) Central, Colombia

IT Services and IT Consulting · 10,001+ employees

Nov 10
data-scientist Senior (5-10 yrs) Full-time Colombia
Create a free account to apply — email only, no card. You can also save this posting or score it against your profile with AI.

About the role

Lead the technical migration, validation, optimization, and industrialization of analytical models from SAS to a modern platform based on Azure Databricks, Python, PySpark, and MLflow. Work with data scientists and engineers to provide direction and support informed decisions about products, growth, and engagement.

What they look for

Python PySpark SQL SAS Azure Databricks Apache Spark Delta Lake MLflow Machine Learning Statistical Modeling Feature Engineering Model Validation Model Interpretability Data Pipelines Scikit-Learn XGBoost

Requirements

Requires advanced Python, PySpark, and SQL skills, along with advanced or upper-intermediate SAS knowledge and familiarity with Databricks notebooks. The role also calls for experience with machine learning and statistical methods, model evaluation and stability, cloud data platforms, and modular, reusable, documented programming practices.

Full description

Job Description

El Senior Data Scientist / Data Science Lead será responsable de liderar técnicamente la migración, validación, optimización e industrialización de modelos analíticos desarrollados en SAS hacia una plataforma moderna basada en Azure Databricks, Python, PySpark y MLflow.

Conocimientos Técnicos: Lenguajes y Programación

  • Python avanzado.
  • PySpark avanzado.
  • SQL avanzado.
  • SAS avanzado o intermedio alto.
  • Conocimiento de notebooks en Databricks.
  • Buenas prácticas de programación modular, reutilizable y documentada.

Machine Learning y Estadística

  • Modelos supervisados y no supervisados.
  • Regresión lineal y logística.
  • Árboles de decisión.
  • Random Forest.
  • Gradient Boosting / XGBoost / LightGBM.
  • Clustering.
  • Series de tiempo.
  • Modelos de scoring.
  • Feature Engineering.
  • Validación cruzada.
  • Selección de variables.
  • Interpretabilidad de modelos.
  • Evaluación de desempeño y estabilidad.

Azure Databricks y Plataforma Cloud

  • Azure Databricks.
  • Apache Spark.
  • Delta Lake.
  • MLflow.
  • Databricks Workflows.
  • Azure Data Lake Storage Gen2.
  • Azure Machine Learning, deseable.
  • Unity Catalog, deseable.
  • Integración con pipelines de datos.

Librerías de Python

  • Pandas.
  • NumPy.
  • Scikit-learn.
  • Statsmodels.
  • PySpark MLlib.
  • XGBoost.
  • Matplotlib.
  • Seaborn.
  • MLflow.
  • SHAP o librerías de explainability, deseable.

Job Description - Grade Specific

Responsible for helping the company leverage data, working with the team of data scientists and engineers to provide valuable direction and make informed decisions concerning the product, growth, and engagement

Similar roles