LUKE ANTHONY BRYAN

• Led QA planning and execution for the VCS 3.16.0 hardening release, coordinating structured test passes, exploratory testing, and cross-team validation while proactively addressing blockers to support release readiness. Recognized with Emerald and Diamond awards for QA leadership and release ownership.
• Led automation efforts for calling features in Stryker Sync, owning end-to-end validation across iOS and Android platforms
• Designed and developed a custom audio call validation solution (“SmartRig setup”), enabling reliable capture and verification of real-time call audio
• Built an AI-driven audio validation pipeline using AssemblyAI (Speech-to-Text) + FFmpeg, improving validation accuracy of voice calling workflows by 40%
• AI-Powered Automation: Integrated Model Context Protocol (MCP) servers with Cursor AI to enhance automation workflows, leveraging AI agents and MCP integrations to support self-healing automation and automate interactions with tools such as Jira and Appium.
• Engineered a hybrid automation architecture for Android using Wireless ADB + wired audio routing, overcoming platform limitations and enabling stable automation execution across devices
• Designed and built a scalable automation framework from scratch for a new team (VCS) using Java, Appium, TestNG, and POM, increasing test coverage and reducing manual testing effort upto 60%
• Integrated REST Assured for API-based validation, enabling end-to-end testing by combining UI automation with backend speech-to-text verification
• Conducted product demos and knowledge-sharing sessions for cross-functional and onsite teams, receiving strong stakeholder feedback
• Authored comprehensive setup documentation for calling and audio automation, enabling faster onboarding for new team members
• Performed code reviews and contributed to test architecture improvements, ensuring code quality.

• Performed functional, regression, and sanity testing for the Apple Support App; executed automated scripts with Appium, TestNG, and XCUITest across iOS, iPadOS, and VisionOS, boosting coverage by 50%.
• Collaborated cross-functionally on 15+ major releases by defining test plans, acceptance criteria, and project documentation, raising 500+ critical bugs that improved app quality.
• Developed automation scripts in Python, Java, and Swift, leveraging Eclipses and Xcode IDEs to streamline test execution and reduce manual effort by 60% and runtime by 40%.
• Designed and implemented a Page Object Model (POM) framework, enhancing script reusability and cutting maintenance effort by 45%.
• Led Conversational AI / GenAI validation (Chatbot Juno) by executing test cases to benchmark accuracy and contextual relevance, while validating LLM-generated prompts and responses.
• Contributed to AI red-teaming, model benchmarking, and evaluation by participating in testing activities to assess AI model behavior, response quality, and potential failure scenarios, supporting the identification of model weaknesses and reliability improvements.
• Partnered with AI/ML and product teams to refine chatbot models, enhance performance, and improve customer experience.

• Performed Web app testing using manual and Selenium automation executing 250+ test cases.
• Detected 150+ critical defects, reducing production issues by 35% and cutting regression time by 40%. Collaborated with Agile teams, improving sprint delivery by 20%.

CGPA - 7.75

GPA: 7.68 CGPA