QA Automation with LLM AI
San Jose CA
Job Description:
- Design and run intelligent test strategies for LLM and agent-based systems combining classic QA and test automation skills with a deep understanding of agentic automationand conversational AI
Responsibilities
- Design and execute end-to-end test plans for UX / Uber orchestrator/ Sub Agents . Build and maintain agentic AI test suites validating autonomous . Develop test data and synthetic scenarios for edge cases ambiguous queries and multilingual requests.
- Evaluate agent behavior through reasoning traces tool-use decisions and memory usage.
- Implement and improve automated testing frameworks leveraging AI for conversational flows APIs and integrations.
- Collaborate with Product management / cross-functional teams to refine requirements and acceptance criteria.
- Document defects test results and insights clearly for stakeholders.
Skill Set
- Minimum 5 years of experience in software QA / test engineering. Strong understanding of testing principles: functional regression integration performance.
- Hands-on experience testing AI or ML systems such as LLM chatbots or recommendation engines.
- Familiarity with key concepts of multi-agentic systems agentic frameworks (e.g. LangChain) AWS AgentCore.
- Scripting skills in Python and experience with REST API testing
- Hands on experience with AI and Machine Learning (ML) techniques to enhance test automation such as generating test cases predicting potential defects or updating test code for user interface changes.
- Hands on experience with test automation frameworks and tools like Selenium Playwright or Cucumber using scripting languages like Python Java or JavaScript and leveraging AI to improve productivity .
- Excellent analytical documentation and communication skills
- Collaborate with cross-functional teams for requirements clarifications and acceptance criteria.
- Document defects test results and insights clearly for stakeholders.
QA Automation with LLM AI San Jose CA Job Description: Design and run intelligent test strategies for LLM and agent-based systems combining classic QA and test automation skills with a deep understanding of agentic automationand conversational AI Responsibilities Design and execute end-to-e...
QA Automation with LLM AI
San Jose CA
Job Description:
- Design and run intelligent test strategies for LLM and agent-based systems combining classic QA and test automation skills with a deep understanding of agentic automationand conversational AI
Responsibilities
- Design and execute end-to-end test plans for UX / Uber orchestrator/ Sub Agents . Build and maintain agentic AI test suites validating autonomous . Develop test data and synthetic scenarios for edge cases ambiguous queries and multilingual requests.
- Evaluate agent behavior through reasoning traces tool-use decisions and memory usage.
- Implement and improve automated testing frameworks leveraging AI for conversational flows APIs and integrations.
- Collaborate with Product management / cross-functional teams to refine requirements and acceptance criteria.
- Document defects test results and insights clearly for stakeholders.
Skill Set
- Minimum 5 years of experience in software QA / test engineering. Strong understanding of testing principles: functional regression integration performance.
- Hands-on experience testing AI or ML systems such as LLM chatbots or recommendation engines.
- Familiarity with key concepts of multi-agentic systems agentic frameworks (e.g. LangChain) AWS AgentCore.
- Scripting skills in Python and experience with REST API testing
- Hands on experience with AI and Machine Learning (ML) techniques to enhance test automation such as generating test cases predicting potential defects or updating test code for user interface changes.
- Hands on experience with test automation frameworks and tools like Selenium Playwright or Cucumber using scripting languages like Python Java or JavaScript and leveraging AI to improve productivity .
- Excellent analytical documentation and communication skills
- Collaborate with cross-functional teams for requirements clarifications and acceptance criteria.
- Document defects test results and insights clearly for stakeholders.
View more
View less