Agentic Testing Engineer(Mandarin)

Agentic Testing Engineer

Job Overview

We are looking for an Agentic Testing Engineer to build the next generation of AI-powered software testing solutions. This role combines AI Agent development, test automation, software engineering, and system-level debugging.

The ideal candidate can leverage LLMs and AI Agents to automate and optimize the testing lifecycle — from test planning and test case generation to test execution, failure analysis, root-cause identification, regression testing, and reporting.

Key Responsibilities

• Design and develop AI Agent-based testing solutions to improve testing efficiency, coverage, and quality.
• Build Agentic workflows that can autonomously:
• Analyze product requirements and specifications
• Generate test plans and test cases
• Select and execute appropriate test scenarios
• Collect test results, logs, and system metrics
• Analyze failures and identify potential root causes
• Create and update JIRA issues
• Trigger regression tests and verify fixes
• Generate test reports and quality insights
• Integrate AI Agents with existing testing infrastructure, including test automation frameworks, devices, APIs, JIRA, Git/Gerrit, CI/CD systems, and log analysis tools.
• Develop reusable tools, APIs, and automation frameworks to enable Agents to interact with real testing environments.
• Evaluate and improve Agent performance, including accuracy, reliability, consistency, tool-use success rate, and hallucination control.
• Develop evaluation datasets and benchmarks for AI-powered testing solutions.
• Apply LLM/RAG technologies to leverage test specifications, historical defects, logs, source code, and testing knowledge.
• Continuously identify opportunities to replace repetitive manual testing activities with AI-driven autonomous workflows.
• Collaborate with software developers, test engineers, and technical teams to integrate Agentic testing solutions into existing development and validation processes.

Required Qualifications

• Bachelor's degree or above in Computer Science, Software Engineering, Electrical Engineering, or a related field.
• 2+ years of experience in software testing, test automation, software development, or related engineering roles.
• Strong Python programming skills.
• Solid understanding of software testing methodologies, including:
• Test strategy and test planning
• Test case design
• Functional and regression testing
• Stress and stability testing
• Failure analysis and root-cause analysis
• Hands-on experience with LLM applications, AI Agents, or AI-assisted software development.
• Understanding of Agent concepts such as planning, reasoning, tool calling, memory, workflow orchestration, and multi-step task execution.
• Experience with Git, Linux, REST API, CI/CD, and software development practices.
• Strong debugging and problem-solving skills with the ability to analyze logs, traces, test results, and system behavior.
• Ability to independently design, implement, debug, and maintain automation solutions.

Client is Google,

You will sign the contract with Neusoft USA, working location is Google office.

Working location is MTV or SanJose

Intern Salary: $26-$30/Hour

Regular Salary：$80000-100000/Year