Key Responsibilities
1. AI & Prompt Engineering Validation
· Design, develop, and execute test cases specifically for AI /ML models, generative AI features, and LLM integrations.
· Apply Prompt Engineering techniques to evaluate model robustness, check for edge cases, and prevent hallucinations or adversarial exploits (jailbreaking).
· Validate the accuracy, relevance, and safety of AI -generated responses against defined benchmarks.
2. Web Application & Automation Testing
· Build, maintain, and scale robust test automation frameworks for modern web applications.
· Integrate automated test suites into the continuous integration/continuous deployment (CI/CD) pipeline.
· Conduct thorough functional, regression, integration, and API testing to ensure flawless user experiences.
3. Strategy & Collaboration
· Collaborate closely with Developers, Data Scientists, and Product Managers to understand AI model behavior and product requirements.
· Identify, document, and track software defects using agile tools, providing detailed steps to reproduce.
· Advocate for QA best practices, specifically regarding data privacy and bias in AI testing.
Required Technical Skills & Qualifications
· Experience: 0 to 2 years of professional experience in software quality assurance with a heavy focus on automation.
· Web Automation: Proven expertise with automation tools and frameworks such as Selenium , Playwright , or Cypress .
· Programming: Strong coding skills in languages like Java / Python (highly preferred for AI /ML tooling) or JavaScript/TypeScript .
· AI /LLM Familiarity: Hands-on experience working with, testing, or prompting AI models (e.g., OpenAI API, Anthropic, open-source LLMs).
· API Testing: Proficient in testing RESTful APIs using tools like Postman, SoapUI, or automated libraries (e.g., Requests, Supertest).
· Tools & Ecosystem: Familiarity with Git, JIRA, and CI/CD tools (e.g., GitHub Actions, Jenkins, GitLab)
Apply through whichever channel suits you best.