- Perform end-to-end QA of data science pipelines and analytics platforms
- Validate data ingestion, transformations, and feature engineering flows
- Conduct model validation, performance benchmarking, and sanity checks
- Identify data leakage, bias, drift, and inconsistencies
- Design and execute platform-level testing (functional, data, and integration testing)
- Validate cross-platform outputs and consistency of analytics results
- Develop automated QA frameworks, validation scripts, and test cases
- Perform regression testing for model and pipeline updates
- Work with DS/Engineering teams to debug, fix, and improve system reliability
- Maintain QA documentation, test coverage, and audit logs
3 Required Skills
- Robust Python (Pandas, NumPy, Scikit-learn)
- Good understanding of ML lifecycle and evaluation metrics
- Experience in:
- Model validation / analytics QA
- Data pipeline testing (ETL validation)
- Platform/system testing
- Strong SQL skills for data validation
- Experience creating test cases, validation frameworks, and automation
4 Good to Have
- Exposure to MLOps / model monitoring / drift detection
- Experience with testing frameworks (PyTest, Great Expectations)
- Knowledge of APIs, microservices testing
- Familiarity with cloud platforms (AWS/Azure)
- Understanding of CI/CD for data and ML pipelines