Mid-Level Data Scientist

Jobtailor; Curitiba; Presencial; BRL 70 000 - 110 000; Tempo integral

Resumo da oferta

Jobtailor in Curitiba, Brazil is seeking a data scientist to develop and deploy predictive models that identify payment propensity and segment customer portfolios. The role emphasizes survival analysis, clustering, and A/B testing to optimize collection strategies.

You will build scalable data pipelines and explore Generative AI applications to enhance service routing and interaction summarization. The candidate should have strong SQL and Python skills, experience with big data tools, and a

Qualificações

• Degree in Data Science or a related field.
• Experience with predictive modeling and database analysis to identify patterns.
• Intermediate to advanced SQL, including CTEs, Window Functions, and query optimization for large data volumes.
• Python, with experience using Pandas or Polars and handling complex datasets.
• Knowledge of Machine Learning, including supervised models such as Logistic Regression, XGBoost, or LightGBM.
• Knowledge of clustering and segmentation.
• Knowledge of Survival Analysis.
• Experience conducting and analyzing A/B tests.
• Experience or a strong interest in collection metrics, credit recovery, risk, or telemarketing/mailing campaigns.
• Experience with time-to-event modeling and advanced knowledge of Survival Analysis (a plus).
• Big Data experience using PySpark or Rust (a plus).
• Knowledge of MLOps, including Docker, Git, and model deployment (a plus).
• Knowledge of applied Generative AI and LLMs (a plus).

Responsabilidades

• Develop and implement supervised and unsupervised predictive models to identify payment propensity, contactability, and segmentation of customer portfolios and profiles
• Build survival models to identify the optimal investment period for collection actions, considering effort, channels, initial contact, meaningful contact, and agreement completion
• Analyze and model the saturation curve of collection actions, seeking to optimize contact strategies and reduce channel fatigue
• Build robust analytical datasets using advanced queries, preparing data for model consumption and analysis
• Apply A/B tests to evaluate strategies and identify improvement opportunities
• Explore and apply Generative AI and LLM solutions in initiatives such as service optimization, routing, and interaction summarization
• Support the advancement of Data Intelligence initiatives by keeping pace with data growth and generating analyses that contribute to more efficient collections

Conhecimentos

Predictive Modeling

SQL

Python

Machine Learning

Survival Analysis

A/B Testing

Clustering

Segmentation

Big Data

Data Analysis

Formação académica

Degree in Data Science or related field

Ferramentas

Pandas

Polars

PySpark

Docker

Git

Descrição da oferta de emprego

• Develop and implement supervised and unsupervised predictive models to identify payment propensity, contactability, and segmentation of customer portfolios and profiles
• Build survival models to identify the optimal investment period for collection actions, considering effort, channels, initial contact, meaningful contact, and agreement completion
• Analyze and model the saturation curve of collection actions, seeking to optimize contact strategies and reduce channel fatigue
• Build robust analytical datasets using advanced queries, preparing data for model consumption and analysis
• Apply A/B tests to evaluate strategies and identify improvement opportunities
• Explore and apply Generative AI and LLM solutions in initiatives such as service optimization, routing, and interaction summarization
• Support the advancement of Data Intelligence initiatives by keeping pace with data growth and generating analyses that contribute to more efficient collections

Requirements

• Degree in Data Science or a related field
• Experience with predictive modeling and database analysis to identify patterns
• Intermediate to advanced SQL, including CTEs, Window Functions, and query optimization for large data volumes
• Python, with experience using Pandas or Polars and handling complex datasets
• Knowledge of Machine Learning, including supervised models such as Logistic Regression, XGBoost, or LightGBM
• Knowledge of clustering and segmentation
• Knowledge of Survival Analysis
• Experience conducting and analyzing A/B tests
• Experience or a strong interest in collection metrics, credit recovery, risk, or telemarketing/mailing campaigns
• Experience with time-to-event modeling and advanced knowledge of Survival Analysis (a plus)
• Big Data experience using PySpark or Rust (a plus)
• Knowledge of MLOps, including Docker, Git, and model deployment (a plus)
• Knowledge of applied Generative AI and LLMs (a plus)

Core Competencies

Demonstrates expertise in predictive modeling, data analysis, and machine learning techniques to optimize customer collection strategies. Proficient in SQL and Python for handling complex datasets and implementing advanced analytical solutions.

Highest-signal resume keywords

• Predictive Modeling
• SQL Query Optimization
• Python Programming
• Machine Learning Techniques
• A/B Testing

ATS Optimization Keywords

Hard Skills

• Predictive Modeling
• SQL
• Python
• Machine Learning
• Survival Analysis
• A/B Testing
• Clustering
• Segmentation
• Big Data
• Data Analysis

Industry Keywords

• Data Science
• Credit Recovery
• Risk Management
• Telemarketing
• Mailing Campaigns

Tools & Technologies

• Pandas
• Polars
• PySpark
• Docker
• Git