We are seeking a Lead AI Engineer to design and implement agentic test automation solutions for a 12+ month contract engagement based in McLean, Virginia. This role focuses on building reusable patterns, establishing quality governance, creating GenAI-assisted reporting across microservices, and implementing automated quality gates—deliverables intended for adoption across multiple engineering teams. Responsibilities Design and implement agentic testing patterns adoptable by multiple teams, including reference implementations demonstrating test generation assistance, test maintenance assistance, and failure analysis assistance. Establish a standard architecture for test code organization, tagging, data management, and execution across UI, API, and service layers. Define and publish coverage standards specifying minimum coverage expectations by service/component, test type mix, and risk-based prioritization with traceability to requirements. Create reusable templates across teams, including test plan templates, test case/spec templates (Gherkin-style or equivalent), and Definition of Ready/Definition of Done quality checklists. Develop a scalable tagging and metadata strategy to support reporting and quality gates. Build automated reporting that aggregates test and service data across multiple microservices, including test execution results, service health signals, and defect signals. Generate GenAI-driven summaries including release readiness narratives, failure clustering and trend analysis, and change-correlation insights. Produce outputs consumable by engineering leadership and teams via dashboards, markdown summaries in pull requests, and artifacts in CI pipelines. Build automated review agents that evaluate user stories and requirements for clarity and completeness before development and testing begin, including validation of acceptance criteria, identification of ambiguities, and assessment of data and privacy considerations. Integrate quality gates into GitHub workflows, including PR checks, issue templates, and GitHub Actions, to reduce churn and rework. Qualifications Required Hands-on experience building LLM-powered agents with tool-using, multi-step reasoning, and guardrails. Experience with prompting patterns, structured outputs (JSON schemas), evaluation techniques, and hallucination reduction. Ability to design agent workflows for test generation and augmentation, requirements review and completeness validation, and report generation and summarization. Strong proficiency with GitHub Copilot in day-to-day development. Deep experience with GitHub platform capabilities including GitHub Actions (CI/CD pipelines, reusable workflows, composite actions), PR checks, branch protections, CODEOWNERS, and templates. Experience with GitHub APIs and webhooks as needed. Advanced experience designing and implementing test automation with Karate (API testing, contract-like checks, data-driven testing, mocks). Advanced experience designing and implementing test automation with Playwright (UI automation, selectors strategy, parallelization, trace and video artifacts). Strong understanding of test design and coverage including happy path scenarios, negative and validation scenarios, edge and boundary scenarios, and data setup/teardown strategies with test isolation. Proven ability to aggregate and normalize results from multiple microservices and multiple pipelines. Experience producing actionable automated reports including trend analysis, failure clustering, and service correlation. Experience implementing automated checks that validate acceptance criteria completeness, required test data and environment dependencies, and non-functional requirements such as performance, security, and observability when applicable.