Senior Data Scientist

Jobtailor; Brasil; Presencial; BRL 150 000 - 210 000; Tempo integral

Resumo da oferta

Jobtailor is seeking a data scientist specializing in master data management to build models, improve data quality, and leverage graph analytics for financial institutions.

You will collaborate with business and engineering teams, deploy Azure Databricks and Graph Data Science workflows, and apply GenAI techniques to enhance data governance and enrichment.

Qualificações

• Bachelor's degree or higher in a quantitative field and relevant experience.
• Experience building statistical and predictive models and applying data quality practices.
• Familiarity with cloud environments and AI platforms.

Responsabilidades

• Conduct studies and analyses to identify gaps, inconsistencies, and opportunities for improvement in customer/master data.
• Build statistical and predictive models for inference, recommendation, and data enrichment.
• Develop Golden Record models to ensure the best version of the customer record.
• Use graph techniques to identify complex relationships in the master data.
• Work with large volumes of structured and unstructured data.
• Apply data profiling, imputation, and enrichment techniques.
• Collaborate with business and engineering teams to improve data quality.
• Support governance initiatives and MDM projects.
• Document methodologies, processes, and results clearly and accessibly.

Conhecimentos

Statistical Modeling

Predictive Modeling

Data Quality Practices

Graph Modeling

Collaboration

Documentation

Data Profiling

Python

SQL

Linear Regression

Logistic Regression

Decision Trees

Formação académica

Bachelor's degree in Statistics, Mathematics, Data Science, Engineering, Economics, or related fields

Ferramentas

Azure

Databricks

Neo4j

Graph Data Science

Azure ML

Generative AI

Descrição da oferta de emprego

• Conduct studies and analyses to identify gaps, inconsistencies, and opportunities for improvement in customer/master data.
• Build statistical and predictive models for inference, recommendation, and data enrichment.
• Develop Golden Record models to ensure the best version of the customer record.
• Use graph techniques to identify complex relationships and opportunities in the master data, such as link detection, clustering, and relationship patterns between entities.
• Work with large volumes of structured and unstructured data.
• Apply data profiling, imputation, and enrichment techniques.
• Collaborate with business and engineering teams to continuously improve data quality.
• Support governance initiatives and MDM (Master Data Management) projects.
• Document methodologies, processes, and results clearly and accessibly.

Requirements

• Proven experience building statistical and predictive models (Linear and Logistic Regression, Decision Trees, Random Forest, Gradient Boosting).
• Proficiency in Python and SQL.
• Experience with classification and clustering models (K-Means, DBSCAN, etc.).
• Knowledge of graph modeling and analysis (e.g., Neo4j, Graph Data Science) is a strong advantage.
• Experience with cloud environments (preferably Azure and Databricks).
• Bachelor’s degree in Statistics, Mathematics, Data Science, Engineering, Economics, or related fields.
• Experience in financial institutions, banks, and/or insurance companies.
• Knowledge of data modeling and data quality practices.
• Familiarity with Azure ML, Databricks, and other AI platforms.
• Experience with GenAI and modern data science techniques (LLMs, embeddings, multimodal models).
• Participation in corporate master data, CRM, or data governance projects.
• Desirable knowledge of Generative AI (GenAI) and modern data analysis techniques.
• Experience in projects that use graphs for relationship analysis and insight discovery.

Demonstrates expertise in building statistical and predictive models, utilizing Python and SQL for data analysis, and applying data quality practices. Proficient in working with large datasets and implementing data governance initiatives within financial institutions.

Highest-signal resume keywords

• Statistical Modeling
• Predictive Modeling
• Data Quality Practices
• Graph Modeling
• Cloud Environments

ATS Optimization Keywords

Hard Skills

• Statistical Models
• Predictive Models
• Linear Regression
• Logistic Regression
• Decision Trees
• Random Forest
• Gradient Boosting
• Classification Models
• Clustering Models
• Data Profiling

Soft Skills

• Collaboration
• Documentation

Industry Keywords

• Master Data Management
• Data Governance
• Financial Institutions
• Banks
• Insurance Companies

Tools & Technologies

• Python
• SQL
• Azure
• Databricks
• Neo4j
• Graph Data Science
• Azure ML
• Generative AI
• LLMs
• Multimodal Models