Key Responsibilities

1. Test Strategy and Planning
• Define comprehensive test strategies and quality gates for AI/ML models, data pipelines, and AI-integrated applications.
• Design and implement test cases that validate model accuracy, robustness, and scalability under real-world scenarios.
• Work with cross-functional teams to define acceptance criteria and AI-specific quality metrics (e.g., F1-score, precision/recall, latency SLAs).
2. Model Validation and System Testing
• Conduct functional, regression, and adversarial testing for AI/ML systems.
• Validate model outputs for correctness, bias, fairness, and ethical alignment.
• Test and monitor data pipelines for quality, consistency, and lineage
• Execute A/B testing and scenario simulations to assess model behavior under varying conditions.
3. Performance Monitoring and Optimization
• Continuously monitor model performance in production (accuracy, drift, latency, throughput).
• Define and track KPIs such as precision, recall, F1-score, mAP, AUC, etc.
• Work with engineering and data science teams to identify root causes of degradation and recommend retraining or optimization strategies.
4. MLOps Quality and Automation
• Integrate testing into MLOps pipelines (CI/CD/CT) to ensure automated validation at every stage of model lifecycle.
• Implement data validation, drift detection, and model versioning frameworks.
• Enforce reproducibility and traceability across model experiments, training datasets, and deployed artifacts.
5. Governance and Collaboration
• Promote responsible AI practices including explainability, transparency, and risk mitigation.
• Contribute to documentation and audits for AI quality compliance (e.g., ISO 42001, ISO/IEC 24028)
• Educate teams on AI testing techniques and foster a culture of quality.