> DOU
middle
A-listwareQA Engineer
format:Remotecompany:Outsource
jiraazure devops
postmanswaggerseleniumplaywrightazure openaipower platformnlp
> full description
Our Customer:
A technology company developing an AI-based application for enterprise users. The project focuses on delivering accurate, reliable, secure, and user-friendly AI-powered functionality.
You will join a cross-functional team and work closely with developers, AI engineers, product owners, and business stakeholders to ensure the quality of AI features throughout the product lifecycle.
Your Tasks:
- Analyze project requirements, user stories, and AI-related business scenarios.
- Create and execute test cases and test scenarios for AI features and workflows.
- Perform functional, system, integration, regression, and end-to-end testing.
- Validate AI-generated responses for accuracy, relevance, completeness, clarity, and consistency.
- Test different types of user inputs, including valid, invalid, incomplete, and ambiguous queries.
- Identify hallucinations, incorrect or inconsistent responses, bias, and gaps in AI understanding.
- Prepare prompt-based test scenarios and test different prompt variations.
- Verify that AI follows defined instructions, guardrails, business rules, and expected tone.
- Validate AI responses against approved knowledge sources and expected outcomes.
- Test integrations between AI components, APIs, databases, knowledge bases, and third-party or enterprise systems.
- Verify authentication, authorization, role-based access, and data correctness.
- Perform regression testing after changes to prompts, models, APIs, or business logic.
- Maintain reusable regression test suites.
- Test AI behavior in edge cases and unexpected user scenarios.
- Log defects with clear reproduction steps, test data, expected and actual results, and severity.
- Track defects using Jira, Azure DevOps, or similar tools.
- Work closely with developers, AI engineers, product owners, and business stakeholders to resolve issues.
- Provide testing results and release sign-off input.
Required Experience and Skills:
- 3+ years of commercial experience in software testing / QA.
- Strong understanding of functional, regression, system, integration, and end-to-end testing.
- Experience creating test cases, test scenarios, and test data.
- Experience testing AI-based applications, chatbots, APIs, enterprise applications, or similar solutions.
- Experience validating AI-generated outputs for correctness, relevance, and quality.
- Understanding of AI concepts such as prompts, LLM responses, hallucinations, context, and knowledge retrieval.
- Experience with defect tracking tools such as Jira, Azure DevOps, or similar.
- Good analytical and problem-solving skills.
- Strong attention to detail and ability to identify inconsistencies in AI-generated responses.
- Good communication skills and ability to work effectively with cross-functional teams.
Would be a Plus:
- Hands-on experience testing Generative AI, NLP, ML, chatbot, or conversational AI solutions.
- Experience testing RAG-based or knowledge-based AI applications.
- Basic understanding of prompt engineering and LLM behavior.
- Experience with API testing tools such as Postman or Swagger.
- Experience with automation testing tools such as Selenium, Playwright, or similar.
- Knowledge of Azure OpenAI, Azure AI, Microsoft Copilot Studio, Power Platform, or similar AI platforms.
- Understanding of prompt injection, data leakage, access control, and responsible AI testing.
- Experience testing AI integrations with databases, knowledge bases, or third-party services.