Key Responsibilities Design and implement LLM-powered agents supporting tool use, multi-step reasoning, guardrails, structured outputs, and reliable workflows Develop prompting patterns, evaluation approaches, and techniques for reducing hallucinations and improving AI-generated outputs Design agent workflows for test generation and augmentation, requirements review and completeness validation, report generation, and summarization Leverage GitHub Copilot extensively in day-to-day software development and engineering workflows Design and implement reusable agentic testing patterns that can be adopted across multiple Underwriting teams and expanded to other domains Create reference implementations, sample repositories, and templates for AI-assisted test generation, test maintenance, and failure analysis Develop test generation capabilities using requirements, APIs, contracts, and schemas Build test maintenance capabilities for updating selectors and contracts and assisting with flaky test triage Develop failure analysis capabilities for root-cause suggestions, log correlation, and defect drafting Establish standard architecture for test organization, tagging, data management, and execution across UI, API, and service layers Define and publish coverage standards, including minimum coverage expectations, test-type mix, risk-based prioritization, and traceability to requirements Develop reusable test plan, test case/specification, and Definition of Ready/Definition of Done templates Establish scalable tagging and metadata strategies covering features, services, risk, priority, and data sensitivity Build automated reporting that aggregates test execution, service health, and defect signals across multiple microservices Generate GenAI-driven release readiness narratives, failure clustering and trend analysis, and What changed insights using commit and pull request correlations Deliver quality insights through dashboards, Markdown summaries in pull requests, and CI-generated artifacts Build automated review agents that evaluate user stories and requirements for completeness, clarity, testable outcomes, data needs, dependencies, privacy considerations, and environment requirements Integrate AI-powered quality gates into development workflows using pull request checks, issue templates, and GitHub Actions to reduce churn and rework Required Qualifications 8+ years of experience Bachelor's Degree Skills LLM-Powered Agent Development Prompt Engineering GitHub Copilot Karate API Test Automation Playwright UI Automation Test Automation Architecture CI/CD Quality Gate Integration Microservices Test Data Aggregation and Reporting Agentic Testing Pattern Design Test Strategy and Standards Definition Test Planning and Specification Authoring Test Metadata and Tagging Strategy Quality Reporting and Release Readiness Analysis Requirements Review and Completeness Validation Failure Analysis and Root-Cause Investigation AI-Assisted Test Generation and Maintenance Schedule Start date: 2026-09-23