AI QE Architect

Position Overview

We are seeking an AI QE Architect to serve as a dedicated AI Change Agent for our customer. In this role, you will lead the transition from traditional Quality Engineering to an AI-augmented ecosystem. You will be responsible for defining the strategy, building high-impact AI use cases, and modernizing the QE landscape using Generative AI and Agentic frameworks. A critical component of this role is deep familiarity with Claude Code, as it is a core tool within the customer's existing environment.

Core Responsibilities

• Strategy & Assessment: Evaluate the current QE landscape (tools, frameworks, processes, and team maturity). Define and drive a comprehensive Agentic AI-led QE transformation roadmap.

• AI Implementation: Design and implement hands-on AI-driven QE solutions, including:

  • Autonomous Test Generation: Creating test cases and scripts using LLMs.
  • Self-Healing Automation: Building frameworks that automatically adapt to UI/code changes.
  • Intelligent Analytics: Developing defect prediction models and automated triaging systems.
  • Synthetic Data: Implementing AI-driven test data generation.
  • Ecosystem Modernization: Integrate AI capabilities into existing CI/CD pipelines and DevOps workflows to accelerate delivery.
  • Tooling & R&D: Evaluate next-gen QE platforms, build Proof of Concepts (POCs), and develop reusable accelerators for scalable adoption across the enterprise.

• Leadership (Player-Coach): Act as a hands-on technical leader who can both architect high-level strategy and contribute directly to code and implementation.

• Stakeholder Management: Collaborate with business, product, and engineering leadership to communicate progress, outcomes, and the value of AI initiatives.

Technical Skills & Qualifications

• Foundational Experience: 10-14 years of experience in Quality Engineering or Software Development in Test (SDET), with a track record of leading enterprise-scale transformations.

• AI & GenAI Expertise: Proven experience with Agentic AI and GenAI frameworks (e.g., LangChain, CrewAI, AutoGen, or Cursor). Specific knowledge of Claude Code and its application in development/testing workflows. Deep understanding of LLMs and multi-agent systems applied to QE.

• Core QE Proficiency: Expertise in modern automation tools like Playwright, Selenium, or Cypress. Strong grasp of API testing, microservices, and cloud-native architectures. Hands-on experience with GitHub Actions and CI/CD integration. Familiarity with cloud platforms (AWS, Azure, or GCP) in the context of AI and testing.

• Execution: Ability to build POCs from scratch and scale them into production-ready frameworks.

• Communication: Exceptional ability to explain complex AI concepts to non-technical stakeholders and senior leadership.