Automation Testing with Gen AI , RAG , LLM
We are looking for a Quality Assurance Engineer who prides themselves on a functional-first mindset. You are someone who thinks deeply about user journeys, business logic, and "what happens if I click this?" before even writing a script. In this role, you will be responsible for the end-to-end quality of our healthcare automation platformensuring that the core infrastructure is rock-solid while pioneering ways to test our Generative AI integrations.
Key Responsibilities
1. Core Functional Excellence
- End-to-End Testing: Own the functional validation of complex healthcare workflows (e.g., RCM, Patient Access, and Clinical Coding).
- Test Strategy: Design comprehensive test plans and cases that cover happy paths, edge cases, and negative scenarios based on deep business logic.
- API & Data Validation: Perform rigorous API testing and verify data integrity across our platforms, ensuring that backend services communicate flawlessly.
- Regression & Stability: Maintain a robust regression suite to ensure that new AI deployments don't break existing, critical healthcare features.
2. GenAI & LLM Evaluation
- Non-Deterministic Testing: Move beyond "Pass/Fail" to evaluate the quality, relevance, and safety of LLM-generated responses.
- RAG Validation: Test the accuracy of our Retrieval-Augmented Generation (RAG) systemsensuring the AI is pulling the correct clinical data and citing it accurately.
- Failure Analysis: Investigate why the AI might fail in downstream processing (e.g., OCR extraction errors or logic hallucinations) and work with devs to refine prompts.
- Model Comparison: Help benchmark different models (OpenAI, Gemini, Llama) to ensure functional consistency as we swap or upgrade engines.
What You Bring
- The "Detective" Mindset: You don't just find bugs; you find the root cause. You have a proven ability to think through complex functional logic.
- Core Toolkit: 35 years of experience in QA with proficiency in SQL, API testing (Postman/RestAssured), and Automation (Selenium/Playwright).