Conduct exploratory data analysis (EDA) to identify patterns, trends, and anomalies.
Work with behavioral, transactional, and event-level data from digital platforms.
3. Model Evaluation & Experimentation
Evaluate models using appropriate metrics such as
AUC-ROC, Precision/Recall, F1-score
RMSE, MAE for regression problems
Design and analyze A/B tests and controlled experiments.
Perform cohort analysis and user behavior analysis to validate model impact.
Iterate on models to improve accuracy, stability, and business relevance.
4. Deployment & Operationalization
Collaborate with AI/ML engineers to deploy models into production environments.
Support integration of models into APIs and downstream applications.
Ensure models are production-ready, scalable, and maintainable.
Monitor model performance and data drift in collaboration with MLOps teams.
5. Collaboration & Business Impact
Work closely with product, analytics, and engineering teams to define problem statements.
Translate business requirements into data science solutions and modeling approaches.
Communicate insights and model outcomes to technical and non-technical stakeholders.
Support decision-making with data-driven recommendations.
6. Data Quality & Pipeline Support
Work with data engineering teams to ensure high-quality input datasets.
Identify and resolve data inconsistencies or gaps affecting model performance.
Contribute to defining clean, reusable datasets for analytics and ML
3–6+ years of experience in Data Science, Machine Learning, or Applied Analytics roles.
Strong proficiency in Python (pandas, NumPy, scikit-learn, etc.).
Solid understanding of classical machine learning algorithms and statistics.
Strong SQL skills for data extraction and manipulation.
Experience with feature engineering and model evaluation techniques.
Hands-on experience working with structured and semi-structured data.
Understanding of A/B testing and experimental design.
Familiarity with data visualization tools (Matplotlib, Seaborn, or BI tools like Tableau/Power BI is a plus).
Preferred Skills
Experience in sports analytics, media platforms, or digital engagement ecosystems.
Exposure to time-series analysis and forecasting models.
Knowledge of recommendation systems and ranking models.
Familiarity with cloud platforms (AWS, Azure, GCP).
Basic understanding of MLOps concepts (model deployment lifecycle).
Experience with big data tools (Spark, Databricks, etc.).
Soft Skills
Strong analytical thinking and structured problem-solving ability.
Good communication skills for collaboration across global offshore/onshore teams.
Ability to work independently in a remote delivery model.
Strong attention to detail and data accuracy.
Ability to translate business problems into analytical solutions.