Jason Tur / QA AUTOMATION + AI
Jason Tur profile photo

Jason Tur

QA Automation Lead + AI Engineer
GitHub Contra LinkedIn

Hello

Here’s who I am & what I do

Resume Projects

I’m a QA automation engineer who builds testing systems that don’t just catch bugs — they prevent them, turning complex CI pipelines into smooth, reliable processes. Lately I bring that same rigor to AI: building LLM-powered features and agentic workflows with Python, prompt engineering, RAG, and AI-assisted test automation.

Skills

QA automation & AI tooling I work with

AEM / Angular / React / Mobile QA
Playwright / Cypress / Puppeteer
Selenium / WebDriverIO
Java / Object-oriented testing
SQL / MySQL
Appium 2
Agile methodology
Mobile testing
No-code automation / N8N / Neddle
Planning and implementation
Jenkins / GitLab / Azure DevOps
Postman / SoapUI
GraphQL / Apollo Studio
Database testing
Website / mobile optimization
Cucumber BDD
Black-box / White-box manual testing
Stakeholder updates
Cross-browser testing
Code delivery review
Regression testing
Native mobile app testing
Smart Bear products: Hiptest / Testrail / Zephr
Cloud Practitioner certified
AI agentic coding (Claude Code / Cursor / Copilot)
Large Language Models (GPT / Claude / Llama)
Prompt engineering
Retrieval-Augmented Generation (RAG)
Embeddings & vector search (Pinecone / FAISS / pgvector)
LangChain / LlamaIndex
AI agents / agentic workflows
OpenAI & Anthropic APIs
Hugging Face / Transformers
Python / FastAPI / REST APIs
AWS (Bedrock / Lambda)
AI-assisted test generation
Generative AI / GenAI

Experience

Converted 200+ Cypress tests to Playwright using AI agentic coding.
Regression suite cut ~60% (75 → 30 mins) via API setup + parallel CI.
GitLab CI/CD gates with caching, artifacts, and per-MR blocking on instability.
Playwright framework for AWS/serverless apps; CI-integrated E2E + API checks.
Scaled coverage 84 → 1100+ scenarios; led offshore/remote QA teams delivering releases.
Multi-browser/mobile automation (Selenium/Appium/BrowserStack) across releases.
Built AI agentic + N8N automation that generates and maintains test assets at scale.
Integrated OpenAI/Anthropic LLM APIs with RAG, embeddings & vector search for context-aware tooling.

QA Automation & AI Engineer

ITPIE • Remote • 2026 – Present

  • Apply AI agentic coding (Claude Code, Cursor, GitHub Copilot) to accelerate a large front-end migration (Angular → Blazor / C# / .NET) and clear backlog defects faster.
  • Design and iterate on prompts and orchestrate multi-step AI/automation workflows (N8N) to automate engineering and QA tasks.
  • Integrate OpenAI/Anthropic LLM APIs; experiment with retrieval-augmented generation (RAG), embeddings, and vector search for context-aware tooling.
  • Use Python for AI tooling and automation; evaluate model output quality and build reusable agent workflows.
  • Build agentic and AI-assisted automation that generates, maintains, and optimizes test assets, expands coverage, and cuts repetitive QA work at scale.

Senior QA Automation Engineer

ITPIE • Remote • 2025 – 2026

  • Converted 200+ Cypress tests to Playwright using AI agentic coding methods.
  • Own end-to-end automation with Cypress (JS/TS) for web UI + APIs; lead a small remote QA team.
  • Cut a 200-test regression from ~75 mins to ~30 mins (~60% faster) using API-based preconditions, smarter waits, and parallelization.
  • Integrated Cypress runs into GitLab CI/CD with caching, parallel jobs, artifacts, and per-MR gating.
  • Added API tests for critical services to run before UI suites for faster failure signals.
  • Partner with engineers and PMs in Agile/Scrum to define acceptance criteria and prevent regressions.
  • Built test data utilities (seed/cleanup), env config, and deterministic mocks to reduce flakiness.
  • Used Copilot to triage failures, fix flaky tests, and publish quality reports (pass/fail trends, MTTR).
  • Contributed to quality practices with test strategy proposals and CI/CD improvements.

Senior QA Automation Engineer

ContinuumCloud • Tampa, FL • 2020 – 2025

  • Collaborated with engineering to build automated testing for AWS serverless architecture and end-to-end scenarios.
  • Created and maintained a full Playwright testing framework.
  • Built automated coverage for GraphQL APIs — queries, mutations, schema contracts, and error paths — and wired it into the GitLab pipeline alongside E2E runs.
  • Used Apollo Studio to monitor operation traces and schema evolution, catching breaking changes before production.
  • Identified application weaknesses and targeted areas for automated coverage.
  • Added E2E and API tests to GitLab CI/CD pipelines.
  • Sketched and documented automated software test procedures.
  • Reviewed bug reports and highlighted problem areas for engineering follow-up.

QA Automation Analyst

Royal Caribbean • Miami, FL • 2019 – 2020

  • Created and led an offshore automation team of three engineers.
  • Ran automated scripts across multiple browsers and mobile devices per release cycle.
  • Built automated quality dashboards and daily P1 health checkpoints for stakeholders.
  • Delivered new automation POCs for Java/Angular/React features.
  • Established vendor relationships with BrowserStack and Appium.
  • Defined intake processes, backlog grooming, and verification points with product teams.
  • Set up Jenkins jobs to run automation scripts and maintain CI signals.
  • Used Selenium (Protractor/WDIO) to build automation suites.
  • Increased coverage from 84 scenarios to 1100+ automated scenarios.

AEM QA Lead

Royal Caribbean • Miami, FL • 2018 – 2019

  • Managed offshore QA (6), led daily bug triage, and coordinated releases.
  • Created test plans, risk management docs, and end-to-end testing workflows.
  • Automated quality reports with Power Automate to speed delivery cycles.
  • Supported CI/CD of internal tools across environments.
  • Tested APIs/services with Postman/SOAP UI and delivered automation POCs.
  • Validated across Java, JavaScript, Spring Boot, and .NET stacks.

Support QA

Royal Caribbean • Miami, FL • 2017 – 2018

  • Worked with developers and offshore QA to keep multi-browser/device builds stable.
  • Tested hotfixes and zero-day patches across environments.
  • Diagnosed environment issues and communicated impact to teams.
  • Handled test planning, estimation, and external testing requests.
  • Researched tools to improve QA workflows and maintain quality culture.

Projects

Live + code links for a few things I’ve built.

QA automation

📚
Playwright Wikipedia Test Suite
Repo only
TypeScript · Playwright suite targeting Wikipedia pages
TS Playwright
Code
🧪
Cypress- Nasa.gov
Repo only
JavaScript · Cypress automation experiments
JS Cypress
Code

AI & agentic

🧭
Agentic Job-Hunt Engine
Private
Python · Discovers, scores, and tracks roles across multiple ATS APIs — built and orchestrated with AI agentic coding
Python LLM Agents
🤖
Playwright AI Triage
Repo only
JavaScript · AI that triages automated-test failures and surfaces likely root causes
JS AI Playwright
Code
🌙
Dreamz
Website
JavaScript · LLM-powered dream journal and interpretation app
JS AI Pages
Website

Web apps

💼
LinkedIn Auto Apply
Repo only
TypeScript · Full-stack bot that auto-applies to LinkedIn Easy Apply jobs with a real-time dashboard
TS Next.js Playwright Prisma SQLite
Code
🛒
Publix BOGO Tracker
Website
TypeScript · PWA that matches Publix BOGO deals to your shopping list
TS Next.js Supabase Vercel
Website Code
📝
Venue Reviews
Website
TypeScript · Rotten Tomatoes for live music venues
TS Next.js Vercel
Website Code
🗺️
Harada Grid
Website
JavaScript · layout / utility experiment
JS Vite Pages
Website Code