5-7 years of practical experience with GenAI, LLMs, and agents AI in software quality engineering.
Proven ability to transform technical requirements into actionable test scenarios.
Experience in analyzing requirements to identify gaps, risks, and test coverage.
Hands-on skills in designing multi-agent workflows for testing and analysis.
Expertise in developing AI-driven defect management mechanisms.
Knowledge in AI/LLM-based validation for multilingual content accuracy.
Familiarity with accessibility standards (WCAG 2.2) for automated checks.
Responsibilities
Develop AI-assisted testing processes that enhance software quality engineering.
Convert user stories and specifications into comprehensive test cases.
Build solutions for functional gap analysis and risk assessment.
Design and implement multi-agent workflows for testing and defect analysis.
Create AI-assisted tools for defect identification and classification.
Engage in architectural discussions to define AI-QE solutions and roadmaps.
Lead technical conversations with cross-functional stakeholders around AI solutions.
Benefits
Hybrid work model in Sunnyvale, CA.
Opportunity to work with cutting-edge AI technologies.
Collaborative environment fostering innovation and technical discussions.
Potential for professional growth and development in AI and engineering.
Full Job Description
Location: Sunnyvale, CA (hybrid)
Requirements:
Strong practical experience with GenAI, LLMs and agents AI to software quality engineering and test lifecycle automation .
Ability to convert requirements, user stories, specifications, API contracts and technical documentation into executable test scenarios and test cases.
Experience building solutions that analyze requirements for functional gaps, ambiguity, traceability, risk and test coverage.
Hands-on experience designing multi-agent workflows for requirement analysis, test generation, defect analysis, validation and quality intelligence.
Capability to develop AI-assisted mechanisms for defect identification, classification, deduplication, severity assessment, root-cause analysis and automated defect filing.
Expreience in developing AI/LLM-based validation for multilingual and localized content, including translation accuracy, formatting, connect, truncation, and content consistency.
Strong understanding accessibility standards such as WCAG2.2 with the ability to build AI-assisted automated checks for accessibility violations across web experiences.
Strong experience with Automation frameworks API/UI testing , CI/CD integration, test orchestration, reporting.
Experience building RAG pipelines using embeddings and vector database to ground AI generated test scenarios and validations in approved requirements and product knowledge.
Ability to define the AI-QE Solution architecture, technical roadmap, reusable accelerators, engineering standard, and measurable business outcomes.
Strong hands-on expertise in Python and Java/Typescript with experience integrating LLM and AI services through APIs
Ability to lead technical discussions with QE, engineering, product, and client stakeholders and translate business problems into scalable AI solutions.
Technology Exposure:
LLMs, RAG, Agentic AI, Prompt Engineering, Multimodal AI, AI Evaluation
