Sdet 3

Responsibilities

• AI-Aware Test Automation - Design and maintain Python/Java-based automation frameworks (Selenium, Playwright, TestNG/JUnit) for web, API, and backend services.
• Extend frameworks to test LLM integrations (OpenAI, HuggingFace, RAG pipelines) with prompt validation, hallucination checks, and response consistency tests.
• Implement model benchmarking (latency, accuracy, bias/drift detection) for generative AI features.


• Quality Infrastructure - Integrate tests into CI/CD pipelines (Jenkins, GitHub Actions) with cloud workflows (AWS/GCP).
• Optimize performance testing (JMeter/Locust) for AI endpoints handling high-throughput inference.
• Debug flaky tests in (non-deterministic) AI systems.


• Leadership & Innovation - Mentor junior engineers on AI testing best practices.
• Research tools like LangChain, synthetic data generators, or adversarial testing techniques.
• Advocate for ML-specific quality metrics beyond traditional pass/fail.

Requirements

• 7–9 years in QA automation with strong Python/Java proficiency.
• Hands-on experience with Selenium, Playwright, REST Assured, and CI/CD tools (Jenkins, Docker).
• Solid understanding of SQL/NoSQL databases and cloud platforms (AWS/GCP).
• Exposure to performance testing (JMeter, K6) and scalable test frameworks.
• Experience with LLM testing (prompt engineering, output validation, rubric-based grading).
• Familiarity with OpenAI APIs, HuggingFace, or LangChain.
• Knowledge of synthetic test data generation for edge-case scenarios.
• Autonomy – Thrive in fast-paced, AI-driven environments with minimal supervision.
• Analytical Mindset – Debug complex failures in probabilistic AI systems.
• Communication - Explain technical trade-offs to non-technical stakeholders.