دوام كاملعن بُعد3+ سنوات0 متقدم
عن الوظيفة
🔍 What You'll Do:
Test AI-powered applications, LLM-based systems, and agentic AI workflows.
Design test strategies and test cases for AI features and AI-generated outputs.
Evaluate AI responses for accuracy, relevance, consistency, and hallucinations.
Test AI agents' tool calling, API integrations, decision flows, and task execution.
Identify edge cases, unexpected behaviors, prompt injection vulnerabilities, and failure scenarios.
Build automated tests for AI APIs, agent workflows, and end-to-end scenarios.
Develop evaluation datasets, regression suites, and quality metrics for AI systems.
Investigate failures and collaborate with AI and software engineers to improve reliability.
Validate AI-generated test cases and automated testing results.
🛠️ What We're Looking For:
Strong software QA fundamentals, including test design, exploratory testing, and defect reporting.
Experience with API testing using Postman or similar tools.
Programming skills in Python, JavaScript, or TypeScript.
Understanding of LLMs, prompt engineering, and AI application behavior.
Experience with test automation frameworks such as Playwright, Pytest, or equivalent tools.
Ability to design effective test scenarios for non-deterministic AI outputs.
Strong analytical thinking and attention to detail.
✨ Nice to Have:
Experience testing AI agents and agentic workflows.
Knowledge of LLM evaluation, RAG, embeddings, and hallucination testing.
Familiarity with MCP (Model Context Protocol) and AI tool integrations.
Experience with prompt injection testing, adversarial testing, and AI security.
Experience building AI evaluation frameworks or automated QA systems.