Job Title: Lead AI Engineer – Agentic Test Automation
Location: Tysons, VA (On-site)
Employment Type: Contract (W2 through ZipStaff — No C2C or 1099)

About the Opportunity

ZipStaff is seeking a Lead AI Engineer specializing in Agentic Test Automation to design and scale reusable AI-driven testing capabilities for a leading housing finance organization.

In this role, you will build agentic testing patterns, GenAI-assisted reporting, and automated quality gates that can be adopted across multiple Underwriting teams and eventually broader domains. This is a hands-on technical leadership role focused on creating lasting engineering assets rather than one-off scripts.

What You’ll Do:

Agentic Test Automation Foundation:

Design and implement agentic testing patterns that can be adopted by multiple teams.
Create reference implementations demonstrating test generation assistance (from requirements, APIs, contracts, schemas), test maintenance assistance (auto-updating selectors/contracts, flaky test triage), and failure analysis assistance (root cause suggestions, log correlation, defect drafting).
Establish a standard architecture for test code organization, tagging, data management, and execution across UI, API, and service layers.

Coverage Standards, Templates & Governance:

Define and publish coverage standards (minimum coverage expectations, test type mix, risk-based prioritization, and traceability).
Provide reusable templates for test plans, test cases/specs (Gherkin-style or equivalent), and Definition of Ready / Definition of Done checklists.
Create a scalable tagging and metadata strategy to support reporting and quality gates.

GenAI-Assisted Reporting & Quality Insights:

Build automated reporting that aggregates test and service data across multiple microservices (execution results, service health signals, defect signals).
Generate GenAI-driven summaries including release readiness narratives, failure clustering, trend analysis, and “what changed” insights.
Produce outputs consumable by engineering leadership (dashboards, PR markdown summaries, CI artifacts).

Quality Gates via Agents:

Build automated review agents that evaluate user stories/requirements for clarity, completeness, acceptance criteria, data needs, dependencies, and edge cases before development/testing begins.
Integrate quality gates into GitHub workflows (PR checks, issue templates, GitHub Actions) to reduce churn and rework.

Required Qualifications:

8+ years of professional software engineering or test automation experience, with significant hands-on leadership in modern automation frameworks.
Hands-on experience building LLM-powered agents (tool-using, multi-step reasoning, guardrails, structured outputs, evaluation, hallucination reduction).
Ability to design agent workflows for test generation/augmentation, requirements review, and report generation/summarization.
Strong proficiency with GitHub Copilot in day-to-day development.
Deep experience with GitHub Actions (CI/CD pipelines, reusable workflows, composite actions), PR checks, branch protections, and GitHub platform automation.
Advanced experience designing and implementing automation with Karate (API/contract testing, data-driven testing, mocks) and Playwright (UI automation, selector strategy, parallelization, artifacts).
Strong test design skills covering happy path, negative/validation, edge/boundary scenarios, data setup/teardown, and test isolation.
Proven ability to aggregate and normalize results from multiple microservices and pipelines into actionable automated reports.
Experience implementing automated requirements/quality gate checks.
Ability to work on-site in Tysons, VA.
Must be legally authorized to work in the United States without sponsorship now or in the future.

Preferred Qualifications:

Experience scaling automation or quality engineering practices across multiple teams or domains.
Background in financial services, mortgage, or highly regulated environments.
Familiarity with service health signals (logs, metrics, traces) and issue tracker metadata integration.

About ZipStaff

ZipStaff partners with leading organizations to connect skilled technology professionals with high-impact contract opportunities. We focus on quality matches and long-term success.

To apply, please submit your resume highlighting your agentic/LLM agent development experience, Karate + Playwright automation expertise, and GitHub Actions / Copilot background.

ZipStaff Inc.

Lead AI Engineer – Agentic Test Automation

About the Job