AI Quality Assurance (QA) Engineer

ROLE OVERVIEW
The AI QA Engineer will define and execute quality assurance strategies for AI and data-driven services used in government settings. The role covers functional, performance, data, model, bias, security, API and production-monitoring validation, with a solid focus on traceability and Responsible AI.

Educational Qualifications
B.Tech. or M.Sc. in Computer Science, Data Science, or a related discipline.
Certification in quality assurance, software testing, or test automation is preferred.

Experience
4–6 years of quality assurance experience for AI/ML systems, analytics platforms, or data-driven applications.
Hands-on experience in functional, performance, data-validation, and model-output testing.
Familiarity with testing approaches for NLP, computer vision, and data-centric applications.

Key Responsibilities
Design and execute end-to-end testing strategies for AI services, covering functionality, performance, data quality, model accuracy, fairness, security, and compliance.
Create test plans, test cases,



test data, regression suites, and acceptance criteria tailored to AI/ML applications and government use cases.
Validate model outputs against business requirements, reference datasets, accuracy thresholds, and expected operating conditions.
Conduct fairness testing, bias detection, subgroup analysis, and Responsible AI compliance checks.
Maintain defect logs, evidence, issue severity, root-cause details, and resolution tracking across development, staging, and production environments.
Collaborate with data scientists, ML engineers, business analysts, and product teams to establish model-testing protocols and release gates.
Build and execute automated test suites within CI/CD pipelines for AI services and data workflows.
Validate APIs, microservices, integrations, data pipelines, ETL processes, and database outputs.
Monitor production AI services for performance degradation, model dri

📌 Quality Assurance Engineer Delhi
🏢 Expertshub
📍 Delhi