QA SDET Engineer - AI Testing

Qualifications

• Programming Languages:Proficiency in languages like Python, Java, or JavaScript for test automation and scripting
• Test Automation Frameworks:Experience with tools like Selenium, Appium, Playwright, and testing frameworks like JUnit, TestNG, or pytest
• Knowledge of CI/CD pipelines (Jenkins, GitLab CI, etc.) for integrating testing into the development process
• API Testing:Understanding of RESTful and GraphQL APIs and tools like Postman, RestAssured
• Database Knowledge:Familiarity with SQL and NoSQL databases for testing data-driven aspects of AI models
• Performance & Security Testing:Understanding of performance testing tools (JMeter, Gatling) and security testing (OWASP ZAP)
• SDLC & Testing Methodologies:Deep understanding of the software development lifecycle and various testing methodologies
• AI-Specific Testing Skills:
• AI Testing Methodologies:Understanding of how to test AI models, including functional testing, performance testing, adversarial testing, and bias detection
• AI Risk & Bias Detection:Knowledge of potential risks and biases in AI models and the ability to test for them
• Generative AI Testing:Familiarity with testing generative AI models, including understanding concepts like hallucination, and ability to assess the quality of generated content
• Tools & Technologies:Experience with AI-specific testing tools and platforms like or Applitools (for visual AI testing), and with cloud-based AI services

Responsibilities

• Model Evaluation:Ability to evaluate AI model performance using metrics like accuracy, precision, recall, F1-score, etc
• Prompt Engineering:Understanding of how to craft effective prompts for AI models, especially for testing conversational AI and other applications that rely on natural language

Full Description

Here's a breakdown of the key skills:1. Foundational QA & SDET Skills:

• Programming Languages:Proficiency in languages like Python, Java, or JavaScript for test automation and scripting.

• Test Automation Frameworks:Experience with tools like Selenium, Appium, Playwright, and testing frameworks like JUnit, TestNG, or pytest.

• CI/CD:Knowledge of CI/CD pipelines (Jenkins, GitLab CI, etc.) for integrating testing into the development process.

• API Testing:Understanding of RESTful and GraphQL APIs and tools like Postman, RestAssured.

• Database Knowledge:Familiarity with SQL and NoSQL databases for testing data-driven aspects of AI models.

• Performance & Security Testing:Understanding of performance testing tools (JMeter, Gatling) and security testing (OWASP ZAP).

• SDLC & Testing Methodologies:Deep understanding of the software development lifecycle and various testing methodologies.

2. AI-Specific Testing Skills:

• AI Testing Methodologies:Understanding of how to test AI models, including functional testing, performance testing, adversarial testing, and bias detection.

• Model Evaluation:Ability to evaluate AI model performance using metrics like accuracy, precision, recall, F1-score, etc.

• Prompt Engineering:Understanding of how to craft effective prompts for AI models, especially for testing conversational AI and other applications that rely on natural language.

• AI Risk & Bias Detection:Knowledge of potential risks and biases in AI models and the ability to test for them.

• Generative AI Testing:Familiarity with testing generative AI models, including understanding concepts like hallucination, and ability to assess the quality of generated content.

• Cloud AI Services:Testing applications that leverage cloud-based AI services (e.g., Azure AI, AWS SageMaker).

• Tools & Technologies:Experience with AI-specific testing tools and platforms like or Applitools (for visual AI testing), and with cloud-based AI services.