AI Agent Developer QA Specialization

Key Responsibilities

• Analyze QA workflows to design agent architectures that automate requirement analysis, test generation, defect triage, and reporting.
• Build, fine-tune, and maintain QA agents using frameworks such as LangChain, OpenAI, LlamaIndex, or custom RL approaches.
• Engine prompts and context strategies for LLM-powered test case generation, regression analysis, and intelligent reporting.
• Integrate agents with code repositories, CI/CD systems, test management platforms, and communication tools.
• Collaborate with QA, development, and AI/ML teams to collect requirements and continually improve agent performance.
• Implement agent validation, test coverage measurement, and reliability evaluation for agent-driven QA flows.
• Contribute to the continuous evolution of self-healing and adaptive QA agent features.
• Document agent design, workflows, evaluation metrics, and operational guidelines.

Required Skills & Qualifications

• Bachelor's or Master's in Computer Science, Engineering, or related field.
• 3+ years in QA engineering, automation, or SDET roles.
• 1+ years hands-on developing AI/LLM-based applications or agents (preferably for process automation or software quality).
• Strong programming skills: Python (must); knowledge of JavaScript/TypeScript, Java, or Go is an advantage.
• Proven experience with one or more of: LangChain, OpenAI API, LlamaIndex, Vertex AI, or similar agent and LLM frameworks.
• Experience integrating AI solutions with DevOps toolchains (Jenkins, GitHub, Jira, etc.).
• Deep understanding of software testing lifecycle, automation frameworks, and QA metrics.
• Clear communication skills with an ability to document and explain agent logic and technical rationale.

Bonus/Preferred Skills

• Experience designing agents for software quality test generation, autonomous triage, or regression analysis.
• Familiarity with RAG (Retrieval-Augmented Generation) and prompt tooling.
• Knowledge of agent frameworks (e.g., CrewAI, AutoGen, or similar).
• Contributions to open-source QA-AI tools or published research in autonomous QA.