LWSA

Technical Lead, Data – Credit Modeling

LWSA

full-time

Posted on:

Location Type: Hybrid

Location: São PauloBrazil

Visit company website

Explore more

AI Apply
Apply

Job Level

About the role

  • Development of statistical models: design, test and implement Credit Scoring, billing/invoicing, and expected loss models.
  • Monitor the performance of models in production.
  • Insights extraction: transform raw data into predictive features to improve model accuracy.
  • Identify new data sources (credit bureaus, alternative data) to increase models' predictive power.
  • Present results and recommend changes to credit policies.

Requirements

  • Degree in Statistics, Mathematics, Economics, Engineering, Computer Science or related fields.
  • Strong statistical knowledge.
  • Experience in credit modeling and the end-to-end credit lifecycle.
  • Proficiency with data manipulation tools and model development frameworks.
  • Prior experience in the financial sector, fintechs or payment companies, specifically dealing with credit risk.
  • Knowledge of credit products for legal entities/business customers (desirable).
  • Previous experience in fintechs, sub-acquirers or payment processors (desirable).
Benefits
  • Health insurance;
  • Dental insurance;
  • Meal voucher or food allowance;
  • Childcare assistance;
  • Transportation allowance;
  • Profit-sharing program (PPR);
  • Day off during your birthday month;
  • Life insurance;
  • Wellhub;
  • Férias&Co (travel benefit);
  • Maternity leave of 6 months and paternity leave of 20 days;
  • Flexible working hours;
  • #Secuida - our Quality of Life Program;
  • Partnerships with various establishments and institutions in education, health, leisure, entertainment, and more.
Applicant Tracking System Keywords

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

Hard Skills & Tools
statistical modelingcredit scoringbilling/invoicing modelsexpected loss modelsdata manipulationmodel development frameworkspredictive featuresmodel accuracycredit modelingcredit risk