Skip to content
BackNov 5
Amit M.
Upwork badge

Amit M.

QA Automation & AI Testing | Playwright | DeepEval | Chatbot & RAG QA

Shipping an AI product, chatbot, or SaaS platform? I find the bugs and bad answers your users would find, before launch. I'm Amit, a Senior QA Engineer with 15+ years of experience across web, mobile, API, and AI-powered applications. I specialize in the hardest products to test: LLM chatbots, RAG systems, voice AI agents, and document-processing pipelines, where "it works on my machine" isn't enough. AI, LLM & RAG Testing • RAG evaluation with DeepEval and Ragas: faithfulness, answer relevancy, contextual precision/recall, hallucination rate • Automated LLM regression suites in CI, so every prompt or model change is scored before it ships • Chatbot & conversational AI testing: intent accuracy, context retention, multi-turn flows, fallback handling • Prompt-injection, jailbreak, PII-leak, and guardrail testing • Voice AI agent QA (Vapi, Retell, ElevenLabs): ASR/TTS accuracy, latency, interruptions, call-flow edge cases • OCR & document AI: extraction accuracy, confidence thresholds, messy and handwritten inputs Test Automation • Playwright (TypeScript and Python): Page Object Model, fixtures, parallel runs, visual checks • Selenium and Cypress for existing suites; Appium for mobile • API automation with Postman/Newman and Pytest • CI/CD integration with GitHub Actions, with Allure/HTML reports your whole team can read • Performance and load checks with JMeter and k6 Manual & Exploratory QA • Functional, regression, smoke, and end-to-end testing • Mobile testing on real iOS and Android devices • Cross-browser testing (Chrome, Safari, Firefox, Edge) via BrowserStack • Integration testing for payments (Stripe, Plaid), WhatsApp, CRMs, and automation workflows • Usability and accessibility checks What You Get • A clear test plan and risk assessment before testing starts • Reusable test cases, automation code in your repo, and eval datasets for AI features • Bug reports with steps, screenshots/video, severity, and environment details • A release-readiness summary: what's safe to ship and what isn't Domains I've Tested Healthcare & wellness • Fintech & budgeting • Restaurant & hospitality SaaS • Recruitment & HR tech • E-commerce & subscriptions • Compliance & audit platforms • Marketing automation Real Devices • iOS: iPhone 16 Pro Max, 15 Plus, 14 Pro Max, 14 Plus, 13 Pro Max, 11, XR • Android: Samsung Galaxy S24 Ultra, S21 Plus, A18, OnePlus 9 & 8T, Poco X4, Realme GT Master Edition Why work with me • Senior-level thinking: I test business logic and user risk, not just buttons • Hands-on with AI products, not only traditional apps • Daily updates and fast, clear communication • Comfortable in Agile sprints alongside your developers • Available across US, UK, EU, and Australian time zones Send me your app link, build, or chatbot URL, and I'll reply with a quick testing approach for your product.

🇮🇳Jaipur, India$20/hr100% JSS5.00 (4)Since Sep 2024
GlobeUpwork

Skills

This freelancer has chosen to keep their earnings private.