Passionate QA Engineer specializing in manual, automation, and AI testing. Experienced in Playwright, Cypress, Selenium, Jest, CI/CD pipelines, and LLM evaluation frameworks to ensure software quality, reliability, and response accuracy.
What I doDesigning and executing detailed test cases and suites to ensure maximum functional coverage.
Building end-to-end automation scripts with Playwright, Cypress, and Selenium to improve efficiency and accuracy.
Testing REST and GraphQL APIs using Postman, Newman, and JMeter to validate functionality, performance, and reliability.
Writing SQL queries to verify data integrity, schema validation, and back-end consistency across environments.
Conducting load and stress testing with JMeter to detect bottlenecks and optimize system scalability.
Building AI testing frameworks with Promptfoo, DeepEval, FAISS, and LLM-as-Judge techniques to benchmark chatbot quality and uncover failure patterns before deployment.
End-to-end testing, automation frameworks, performance analysis, and CI/CD pipelines.
End-to-end CI/CD pipeline where GitHub Actions builds Dockerized Playwright tests, Jenkins orchestrates execution, and Kubernetes Jobs run automated tests inside containerized pods.
Designed test cases and executed manual test cycles using Jira & TestRail for coverage tracking.
Developed a lightweight framework to audit LLM behavior using Groq LLaMA3: validating keywords, measuring latency, grading responses, detecting hallucinations, checking safety, and testing paraphrase robustness.
Implemented automated regression tests for OpenCart using Java, Selenium & TestNG.
.png)
Performed load and stress testing of JSONPlaceholder APIs using JMeter, Postman & Jenkins.
Automated drag-and-drop flows, component styling, and user journeys with Cypress E2E testing.
Automated multi-user workflows and session validation in a real-time collaborative coding platform using Playwright.
Validated task management workflows, kanban board, and real-time chat with functional tests in Jest.
Built a GitHub Actions pipeline with custom CLI to automate test execution and reporting across browsers.
Implemented AI-based locator healing using Playwright and Healenium, enabling tests to auto-recover from DOM changes and reduce maintenance time.
Containerized Playwright tests using Docker Compose to automate E2E testing in isolated environments with consistent CI execution.
Built a hybrid LLM evaluation framework using Promptfoo, DeepEval, RAG (FAISS), and Groq to measure answer relevancy, faithfulness, and toxicity while identifying prompt weaknesses through real-world test datasets.
I'll try to answer as soon as possible.