Talha Khan

AI & LLM QA Specialist | Freelance QA Consultant

Upwork • Freelance

Dec 2025 - Present • 9 mos

• Manual QA, Software QA, and AI Product Testing specialist for web, mobile, and AI-native applications • Manual Testing, Functional Testing, and Regression Testing across client projects • Web Testing and Mobile App Testing across responsive and cross-platform builds • AI Testing: LLM output validation, hallucination detection, and prompt injection testing on multi-agent workflows, applying Generative AI testing methodologies • 2 completed AI QA engagements, both rated 5.0 • Automation-capable: Playwright deployed on a completed AI QA project • Bug Tracking & Reports delivered with reproduction steps, severity, priority, and video evidence

SR QA Analyst & Documentation Lead | ISoft Technologies

iSoft Technologies • Temps plein

Dec 2024 - Dec 2025 • 1 yr

• Led end-to-end manual QA and software QA testing across 16+ web, mobile (iOS/Android), E-commerce, SaaS, and event-driven platforms, reducing critical post-release defects by 30%+ through comprehensive risk-based test planning • Designed and executed 500+ functional, regression, UI, usability, and exploratory test cases per sprint, strengthening test case design and sustaining 95%+ test coverage and zero critical escapes across all production releases • Deployed Agentic AI automation workflows using Playwright/Python and AI coding assistants (Claude, Copilot) to auto-generate regression test scripts from user stories and acceptance criteria, reducing test authoring time by 50%+ per sprint • Built AI-assisted test documentation pipelines: used LLM prompts to produce structured test plans, edge case checklists, and release notes from raw Jira tickets, cutting documentation overhead by 40% • Validated 100+ RESTful API endpoints using Postman, verifying data integrity, synchronization

SR Software Quality Assurance Engineer | Black Box Labs

Black Box Labz • Temps plein

Jan 2021 - Dec 2024 • 3 yrs 11 mos

• Executed comprehensive manual testing and software QA for 25+ web and mobile applications (iOS/Android) in Agile environments, supporting 12 major product launches with zero critical production escapes • Performed 1,000+ functional, regression, API, usability, UAT, and compatibility tests, applying structured test case design and maintaining a defect detection rate of 85%+ pre-release, consistently the highest across the QA team • Progressively adopted AI-assisted automation (2023–2024): used ChatGPT and AI coding tools to generate and maintain Playwright/Python test scripts, growing automated coverage from 20% to 60% and contributing to a 40% reduction in manual regression effort per sprint • Validated AI-enabled product features including LLM output accuracy, hallucination detection, and prompt behavior consistency, Generative AI testing that reduced AI-related defects by 35%+ in production • Reviewed 300+ user stories and created 6,000+ structured test cases, with traceability.