AI Quality Assurance Engineer

Role Overview

AI Quality Assurance Engineer at TAWANTECH. Full-time position requiring 5+ years of experience.

Role Purpose

Ensure the quality, reliability, accuracy, and performance of AI/ML solutions throughout the development lifecycle. Develop and implement testing strategies for AI models, data pipelines, AI applications, and production deployments while ensuring solutions meet business, technical, security, and regulatory requirements.

Key Responsibilities

Testing Strategy & Design

• Develop and execute comprehensive QA and testing strategies for AI/ML solutions.
• Design test cases for machine learning models, AI applications, APIs, and data pipelines.
• Establish quality gates and acceptance criteria for AI model deployment.

Model & Data Validation

• Validate AI models for accuracy, consistency, robustness, and performance.
• Perform data quality, data validation, and data integrity testing.
• Test AI outputs for accuracy, bias, hallucination, reliability, and consistency where applicable.
• Monitor model performance and identify model and data drift in production.

Testing Execution

• Conduct regression, integration, functional, performance, and automated testing.
• Automate testing processes and integrate QA activities into CI/CD pipelines.

Governance & Compliance

• Support model governance, auditability, and compliance requirements.
• Document defects, test results, risks, and remediation activities.

Collaboration

• Collaborate with Data Scientists, AI Engineers, Data Engineers, and Business stakeholders.

Qualifications & Experience

• Bachelor's degree in Computer Science, Data Science, AI, Engineering, or a related field.
• 5+ years of experience in QA, AI/ML testing, software testing, or data quality.
• Strong understanding of machine learning and AI lifecycle processes.

Skills & Competencies

• Experience with Python and automated testing frameworks.
• Knowledge of SQL and data validation techniques.
• Experience with APIs, cloud platforms, CI/CD, and version control.
• Understanding of ML model evaluation metrics and model monitoring.
• Strong analytical, problem-solving, and communication skills.