AI Data & Quality Analytics Tester

GenAI / LLM Agent Test Engineer

Experience : 5 to 9 years

Location : Bangalore

Job Summary:

We are looking for a GenAI / LLM Agent Test Engineer to assure quality, reliability, and responsible behavior of LLMbased and RAGbased agents, including singleagent and multiagent workflows. The role focuses on prompt engineering, hallucination detection, agent reasoning validation, and automated evaluation of GenAI outputs using modern LLM testing frameworks.

Key Responsibilities:

• Perform data validation and reconciliation across source-to-target pipelines using SQL and automated checks
• Design and execute test strategies for data quality pipelines, including test data preparation, labeling verification, and schema validation
• Validate predictive quality metrics (trend forecasts, risk scoring, defect leakage signals) for correctness and stability
• Execute defect trend analysis and risk****based testing using telemetry and historical patterns
• Implement automated data validation in CI/CD pipelines and ensure continuous quality gates
• Conduct prompt testing and A/B comparisons for AIassisted analytics interactions (where applicable)
• Leverage LLMs for:
• Intelligent test data generation
• Automated data labeling validation
• AIassisted anomaly detection in data quality pipelines
• Produce actionable insights via statistical thinking and analytical reasoning; communicate quality risks clearly to stakeholders

Qualifications and Skills:

• Bachelors or master’s degree in computer science, Engineering, Data Science, or equivalent experience.
• 6+ years of experience in QA automation or software engineering.
• 3+ years of experience working with AIdriven automation or intelligent testing frameworks.
• Minimum 2 years of handson experience in building or testing AIbased tools or platforms.

Must Have Tools

• SQL (Postgres / Snowflake)
• Pandas / NumPy
• Python (data validation)
• Promptfoo (A/B prompt tests)
• Test data profiling tools
• OpenAI / Azure OpenAI APIs
• Cursor AI / GitHub Copilot / Claude CLI
• PydanticAI