Description
You will validate AI-powered applications, LLMs, RAG pipelines, and backend services to ensure accuracy, safety, and robustness.
Responsibilities
- Design and execute test cases for APIs, backend services, and UI interfaces.
- Evaluate LLM outputs for factual accuracy, hallucinations, bias, and toxicity.
- Perform adversarial testing, including prompt injection and jailbreak scenarios.
- Develop and maintain automation test suites and integrate them into CI/CD pipelines.
- Validate semantic search results in vector databases and test prompt orchestration logic.
- Conduct performance and load testing on model inference APIs and backend services.
Required Skills
- 6+ years of professional software QA experience.
- Proficiency with automation frameworks such as Selenium, Playwright, Cypress, or Pytest.
- Hands-on experience with API testing using Postman or REST-assured.
- Strong understanding of RESTful APIs and backend system validation.
- Familiarity with LLMs, NLP concepts, and GenAI tools like OpenAI, Hugging Face, or LangChain.
- Working knowledge of Git and CI/CD integration.
- Experience testing RAG pipelines and vector database semantic search.
- Ability to perform red-teaming and identify data privacy risks.
- Bachelor's degree in Computer Science, Engineering, or a related field.