Agentic AI with Testing

We are seeking a QA Engineer with expertise in Agentic AI, Generative AI testing, and API/database validation. The ideal candidate should have exposure to LLMs, RAG architectures, prompt testing, and traditional testing methodologies.

Key Responsibilities

• Design, develop, and execute test strategies for AI-powered and Agentic AI applications.
• Validate Large Language Model (LLM) outputs for accuracy, consistency, and reliability.
• Test prompt engineering workflows and optimize prompts for performance and stability.
• Perform API testing for RESTful and SOAP services.
• Execute database testing using SQL queries for data validation and integrity checks.
• Validate RAG pipelines including embeddings, vector databases, and retrieval mechanisms.
• Collaborate with AI engineers, developers, and business teams for requirement analysis and test planning.
• Identify defects, track issues, and ensure high-quality AI application delivery.
• Support automation and Python-based testing initiatives.

Required Skills

• 3+ years of experience in software testing and QA.
• Good understanding of LLMs, Generative AI, and Agentic AI concepts.
• Exposure to frameworks such as LangChain, LlamaIndex, CrewAI, or similar.
• Strong understanding of RAG architectures and vector databases.
• Experience in prompt engineering and AI response validation.
• Hands-on experience in API testing and database testing.
• Knowledge of SQL and Python.
• Strong analytical and debugging skills.

Preferred Skills

• Experience in automation testing frameworks.
• Exposure to AI model evaluation metrics and testing methodologies.
• Familiarity with Agile/Scrum practices.

Educational Qualification

• Bachelors degree in Computer Science, IT, or related field.