ChatGPT Jobs
Sr. AI Integration Specialist - Software Development Engineer in Test
ChatGPT Jobs, Charlotte, North Carolina, United States, 28245
Sr. AI Integration Specialist - Software Development Engineer in Test
Company: SAS Location: Cary, NC (Hybrid or Remote) Salary: $97.30K - $131K/yr (Estimated pay) Job Type: Full-time Benefits: Medical, Dental, Vision, Retirement, PTO Job Description
The AI Navigator team is looking for a Senior Software Development Engineer in Test (SDET) – AI Integration Specialist to pioneer quality engineering methodologies that combine AI assistance with human expertise at enterprise scale. Our team establishes the frameworks and practices that define how AI is integrated into software development while ensuring solutions truly meet user needs through comprehensive end-to-end validation. This is not a standard SDET role. You will be an active Claude power user, working hands‑on with AI tools daily while developing systematic methodologies, confidence frameworks, and quality standards that will guide SAS’s organization‑wide AI adoption. You'll focus on the critical human‑judgment testing areas where AI assistance enhances but cannot replace expert validation. Responsibilities
Lead comprehensive end‑to‑end testing using Claude assistance for AI Navigator features, combining AI‑generated test scenarios with human validation of authentic user workflows and business processes. Develop original confidence scoring methodologies to evaluate AI‑generated test implementations, establishing measurable quality thresholds and review triggers for AI‑assisted testing. Create systematic AI‑human testing frameworks defining when and how to combine Claude assistance with human expertise based on complexity, risk, and business domain requirements. Execute complex user journey and business workflow validation that requires deep domain understanding, using AI tools for planning while applying human judgment for critical validation decisions. Build reusable AI‑assisted testing templates and methodologies for various testing contexts, creating organizational frameworks for sustainable AI integration in quality engineering. Establish quality gates and CI/CD integration protocols connecting AI confidence scores to automated routing and escalation, ensuring AI‑enhanced development maintains quality standards. Be encouraged to participate in open‑source projects on behalf of SAS. Ensure all applicable security policies and processes are followed to support the organization's secure software development goals. Embrace curiosity, passion, authenticity and accountability—values that influence everything we do. Required Qualifications
Bachelor’s degree in computer science, engineering, or related technical field. 8 years of experience in software testing with demonstrable SDET expertise and disciplined testing methodologies. Expert‑level end‑to‑end testing experience including user journey validation, workflow testing, and business scenario validation in enterprise environments. Strong systems thinking and methodology development skills with proven ability to create frameworks and standards that scale beyond individual projects. Advanced test automation mastery (Selenium, Playwright, REST API testing, etc.) with track record of building robust, maintainable test suites. Strong programming proficiency in multiple languages (Python, Java, JavaScript, etc.) with clean coding practices. Business domain testing expertise validating complex workflows, data flows, and integration patterns. Equivalent combination of related education, training and experience may be considered in place of the above qualifications. Additional Competencies, Knowledge & Skills
Technology savvy—essential for leveraging AI tools and sharing expertise about new technology integration. Decision making—critical for developing methodologies and determining when to use AI vs human judgment. Initiating action—important for proactive innovation and methodology development aspects. Experience with AI tools in development workflows (GitHub Copilot, Claude, ChatGPT, etc.). Understanding of prompt engineering and context optimization for AI systems. Background in DevSecOps and security testing automation. Experience with observability tools (monitoring, logging, tracing) across complex environments. Previous experience in pilot programs, innovation labs, or emerging technology initiatives.
#J-18808-Ljbffr
Company: SAS Location: Cary, NC (Hybrid or Remote) Salary: $97.30K - $131K/yr (Estimated pay) Job Type: Full-time Benefits: Medical, Dental, Vision, Retirement, PTO Job Description
The AI Navigator team is looking for a Senior Software Development Engineer in Test (SDET) – AI Integration Specialist to pioneer quality engineering methodologies that combine AI assistance with human expertise at enterprise scale. Our team establishes the frameworks and practices that define how AI is integrated into software development while ensuring solutions truly meet user needs through comprehensive end-to-end validation. This is not a standard SDET role. You will be an active Claude power user, working hands‑on with AI tools daily while developing systematic methodologies, confidence frameworks, and quality standards that will guide SAS’s organization‑wide AI adoption. You'll focus on the critical human‑judgment testing areas where AI assistance enhances but cannot replace expert validation. Responsibilities
Lead comprehensive end‑to‑end testing using Claude assistance for AI Navigator features, combining AI‑generated test scenarios with human validation of authentic user workflows and business processes. Develop original confidence scoring methodologies to evaluate AI‑generated test implementations, establishing measurable quality thresholds and review triggers for AI‑assisted testing. Create systematic AI‑human testing frameworks defining when and how to combine Claude assistance with human expertise based on complexity, risk, and business domain requirements. Execute complex user journey and business workflow validation that requires deep domain understanding, using AI tools for planning while applying human judgment for critical validation decisions. Build reusable AI‑assisted testing templates and methodologies for various testing contexts, creating organizational frameworks for sustainable AI integration in quality engineering. Establish quality gates and CI/CD integration protocols connecting AI confidence scores to automated routing and escalation, ensuring AI‑enhanced development maintains quality standards. Be encouraged to participate in open‑source projects on behalf of SAS. Ensure all applicable security policies and processes are followed to support the organization's secure software development goals. Embrace curiosity, passion, authenticity and accountability—values that influence everything we do. Required Qualifications
Bachelor’s degree in computer science, engineering, or related technical field. 8 years of experience in software testing with demonstrable SDET expertise and disciplined testing methodologies. Expert‑level end‑to‑end testing experience including user journey validation, workflow testing, and business scenario validation in enterprise environments. Strong systems thinking and methodology development skills with proven ability to create frameworks and standards that scale beyond individual projects. Advanced test automation mastery (Selenium, Playwright, REST API testing, etc.) with track record of building robust, maintainable test suites. Strong programming proficiency in multiple languages (Python, Java, JavaScript, etc.) with clean coding practices. Business domain testing expertise validating complex workflows, data flows, and integration patterns. Equivalent combination of related education, training and experience may be considered in place of the above qualifications. Additional Competencies, Knowledge & Skills
Technology savvy—essential for leveraging AI tools and sharing expertise about new technology integration. Decision making—critical for developing methodologies and determining when to use AI vs human judgment. Initiating action—important for proactive innovation and methodology development aspects. Experience with AI tools in development workflows (GitHub Copilot, Claude, ChatGPT, etc.). Understanding of prompt engineering and context optimization for AI systems. Background in DevSecOps and security testing automation. Experience with observability tools (monitoring, logging, tracing) across complex environments. Previous experience in pilot programs, innovation labs, or emerging technology initiatives.
#J-18808-Ljbffr