Design and execute generative AI testing scenarios, including exploratory testing for chatbot interactions, intent recognition, tone, and edge-case behavior.
Experience with designing and executing conversational agents.
Experience in LLM test designs, including prompt and grounding validation, golden sets, and non-deterministic assertions.
Perform crucial safety and quality checks, such as testing for hallucination, bias, toxicity, and PII leakage.
Validate structured and unstructured data outputs, ensuring consistency, accuracy, and compliance.
Establish and drive real-time testing approaches, including streaming data validation and API monitoring.
Collaborate with ML and NLP teams to define comprehensive evaluation metrics and criteria for agent performance.
Integrate AI-driven tools (like Copilot or Claude) into the QA lifecycle to accelerate test design, documentation, and defect analysis.
Strong experience with automation testing with JS, Python
Requirements
Fluent Arabic language skills (spoken and written)
8+ years of experience in QA engineering, with proven experience in automation tests
5+ years of experience in testing data systems
Strong experience in using AI applications for testing
Strong analytical skills and attention to detail, capable of spotting subtle inconsistencies in data and agent behavior.
Experience with API testing (manual and automated)
Familiarity with chatbot frameworks, LLMs, or conversational testing.
Experience in using LLM-based assistants (e.g., GitHub Copilot, ChatGPT) in test and execution.
Exposure to QA automation tools (e.g., PyTest, Postman, dbt tests).