Lead Data Scientist

EPAM Systems; Brasil; Remote; BRL 200,000 - 320,000; Full time

Job summary

EPAM Systems seeks a Lead Data Scientist to drive core modeling execution across multiple algorithmic families, including time series forecasting and anomaly detection in historical demand data.

You will conduct model bake-offs, select champion models based on cross-validation and business-defined metrics, track experiments with MLflow, and partner with Data Engineering and BI teams to ensure seamless feature delivery and prediction consumption within the Microsoft Fabric environment.

Qualifications

• Advanced degree or equivalent in Data Science, Statistics, Operations Research, or Computer Science.
• Expertise in Time Series Forecasting, Machine Learning, and mathematical optimization.
• Proficiency in Python and ML libraries such as LightGBM, XGBoost, and Scikit-learn.
• Familiarity with Prophet and Optuna.
• Experience with MLflow and validation methodologies such as walk-forward CV.

Responsibilities

• Conduct model experimentation and bake-offs across multiple algorithmic families (tree-based regressors, forecasting, deep learning, optimization).
• Select and justify the champion model based on cross-validation and business-defined error metrics.
• Implement anomaly detection algorithms to identify outliers and disruptions in historical demand data.
• Track and log experiments using MLflow within the Microsoft Fabric environment.
• Partner with Data Engineering and BI teams to ensure seamless feature delivery and prediction consumption.

Skills

Time Series Forecasting

Machine Learning

Mathematical optimization

Python

LightGBM

XGBoost

Scikit-learn

Prophet

Optuna

MLflow

Walk-forward CV

Education

Advanced degree or equivalent in Data Science, Statistics, Operations Research, or Computer Science

Tools

LightGBM

XGBoost

Scikit-learn

Prophet

Optuna

MLflow

Job description

We are seeking a Lead Data Scientist to drive core modeling execution, including running competitive model bake-offs, selecting champion models, performing model evaluation, and implementing anomaly detection.ResponsibilitiesConduct model experimentation and bake-offs across multiple algorithmic families (tree-based regressors, statistical forecasting, deep learning, optimization)Select and justify the champion model based on cross-validation and business-defined error metricsImplement anomaly detection algorithms to identify outliers and operational disruptions in historical demand dataTrack and log experiments using MLflow within the Microsoft Fabric environmentPartner with Data Engineering and BI teams to ensure seamless feature delivery and prediction consumptionRequirementsAdvanced degree or equivalent experience in Data Science, Statistics, Operations Research, or Computer ScienceExpertise in Time Series Forecasting, Machine Learning, and mathematical optimizationProficiency in Python and modern ML libraries such as LightGBM, XGBoost, and Scikit-learnFamiliarity with Prophet and OptunaExperience with experiment tracking using MLflow and validation methodologies such as walk-forward CVProfessional English proficiency (B2+/C1)We offerInternational projects with top brandsWork with global teams of highly skilled, diverse peersHealthcare benefitsEmployee financial programsPaid time off and sick leaveUpskilling, reskilling and certification coursesUnlimited access to the LinkedIn Learning library and 22,000+ coursesGlobal career opportunitiesVolunteer and community involvement opportunitiesEPAM Employee GroupsAward-winning culture recognized by Glassdoor, Newsweek and LinkedInEPAM is an Equal Opportunity Employer. All qualified applicants will receive consideration for employment without regard to race, color, religion, sex, national origin, age, sexual orientation, gender identity or expression, disability, protected veteran status, or any other characteristic protected by applicable law.