LLM Evaluation Framework
Automated evaluation for LLM outputs, RAG accuracy, and hallucination scoring
E2E, API, and performance automation — each backed by CI/CD pipelines and live reports.
LLM evaluation frameworks, RAG benchmarks, and Promptfoo security red-teaming
Automated evaluation for LLM outputs, RAG accuracy, and hallucination scoring
LLM vulnerability scanning, jailbreak testing, and red teaming with Promptfoo
Cross-browser automation with Playwright and Cypress BDD
TypeScript-first, cross-browser test suite targeting saucedemo.com
Typed spec files with reusable commands and Mochawesome reports
Gherkin feature files with JavaScript step definitions
OpenAPI schema validation and Pact consumer-driven contract testing
Automated schema & API contract validation against OpenAPI / Swagger specs
Consumer-driven contract testing for microservices using Pact
k6 load testing, Supertest API validation, and Postman collections
Performance & Load Testing
API Testing
API Collections
Selenium Java test suites built with JUnit 5 and TestNG data providers
Clean POM architecture with JUnit 5 runner and Allure reporting
@DataProvider matrix covering all 5 saucedemo accounts