Designation: AI QA Engineer
Educational Qualification:
- B. Tech / M.Sc. in Computer Science, Data Science, or related fields.
- Certification in Quality Assurance or Test Automation preferred.
Experience:
- 4–6 years in quality assurance for AI/ML systems or data-driven platforms.
- Experience in functional, performance, and data validation testing of AI models.
- Familiarity with testing frameworks for NLP, CV, and data-centric applications.
Key Responsibilities:
- Design and execute comprehensive testing strategies for AI services including functional, performance, and bias testing
- Create detailed test plans, test cases, and regression testing suites specifically tailored for AI/ML applications and government use cases
- Perform model validation testing, data quality assessment, and AI output accuracy verification against business requirements
- Conduct fairness testing, bias detection, and ethical AI compliance validation for government AI applications
- Maintain comprehensive logs of defects, issues, and resolution tracking across development, staging, and production environments
- Collaborate with data scientists and ML engineers to establish testing protocols for model performance and reliability
- Execute automated testing frameworks for continuous integration and deployment of AI services
- Validate AI service integration points, API functionality, and data pipeline integrity
- Monitor production AI systems for performance degradation, accuracy drift, and compliance violations
Technical Competencies:
- AI Testing: Model validation, bias detection, fairness testing, AI output verification, and responsible AI compliance testing
- Test Automation: Selenium, pytest, TestNG, Cypress for automated testing frameworks and continuous integration
- Programming Languages: Python for test scripting, SQL for data validation, basic understanding of R for statistical testing
- Testing Tools: Jira, TestRail, Postman for API testing, Jenkins for CI/CD testing pipelines
- Data Validation: Data quality testing, ETL testing, data pipeline validation, and database testing techniques
- Performance Testing: Load testing, stress testing, and performance monitoring for AI services and data processing systems
- Security Testing: Data privacy validation, access control testing, encryption verification, and compliance audit support
- Cloud Testing: AWS, Azure, GCP testing environments, cloud service validation, and multi-environment testing strategies
- API Testing: REST API testing, GraphQL testing, microservices testing, and integration testing methodologies