Data Scientist, Mid-Level

PagBank

. Develop end-to-end predictive models for Credit and Collections, including target definition, feature engineering, and deployment.

Posted 10/6/2026full-timeSão Paulo • BrazilMid-LevelSeniorWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in developing predictive models for Credit and Collections, utilizing machine learning techniques and statistical analysis. Proficient in translating business needs into data-driven solutions while ensuring compliance with AML regulations.

Highest-signal resume keywords

Predictive ModelingMachine LearningApplied StatisticsPython ProficiencySQL Proficiency

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

Predictive ModelingApplied StatisticsClassification ModelsRegression ModelsFeature EngineeringData ManipulationRisk Domain KnowledgeModel MonitoringProbability-of-Default ModelsFraud Detection Models

Soft Skills

CollaborationCommunicationPresentation Skills

Tools & Technologies

PythonRSQLSparkAWSAzureGCPGitHubLLMsPrompt Engineering

Industry Keywords

Credit and CollectionsAML RegulationsData-Driven SolutionsFeature StoresTarget Book Creation

Tech Stack

Tools & technologies

AWSAzureCloudGoogle Cloud PlatformPythonSparkSQL

About the role

Key responsibilities & impact

Develop end-to-end predictive models for Credit and Collections, including target definition, feature engineering, and deployment.
Conduct exploratory analyses, segmentation, and ad hoc studies to identify opportunities and mitigate risks.
Optimize processes and continuously improve models.
Collaborate with engineering and product teams to ensure solution scalability.
Translate business needs into data-driven solutions.
Prepare executive presentations with recommendations and insights for technical and non-technical audiences.
Develop probability-of-default models using machine learning.
Develop models to detect fraud in financial transactions.
Implement models to monitor compliance with AML regulations.
Support the development of models for predictive collections strategies.

Requirements

What you’ll need

Bachelor’s degree in Statistics, Mathematics, Computer Science, Engineering, or a related field.
Proficiency in Python, R, and SQL.
Strong knowledge of applied statistics and data science.
Experience with classification models, including Random Forest, XGBoost, and LightGBM, as well as regression models.
Knowledge of target book creation in the risk domain.
Knowledge of covariate book creation, feature engineering, and feature stores.
Experience with data structures and manipulation in Spark.
General knowledge of cloud platforms: AWS, Azure, or GCP.
Experience with GitHub.
Basic knowledge of LLMs, including GPT, Claude, Gemini, and Llama.
Understanding of model limitations, including hallucinations, context, and bias.
Familiarity with Prompt Engineering.

Benefits

Comp & perks

Meal and/or food allowance.
Health and dental insurance.
Life insurance.
Partnerships with TotalPass and ZenKlub.
Extended maternity and paternity leave.
Childcare assistance.
Discounts of up to 50% on graduate programs and MBAs at leading institutions such as FIA, FAAP, and PUCRS.
No dress code.
Birthday day off.
Baby Gift: gift for newborns.