Haystack
← Back to Jobs
Technology
CI

Lead AI Engineer Agentic Test Automation

ChaTeck IncorporatedMcLean, VA🇺🇸United StatesPosted 25 Aug 2026

Why This Role Stands Out

You will pioneer cutting-edge AI-driven test automation solutions within a reputable technology consulting firm, gaining significant experience with LLM-powered agents and CI/CD pipelines. This hybrid role is ideal for a skilled engineer passionate about shaping the future of quality assurance and driving impactful innovation. Apply today to join a team dedicated to delivering transformative solutions.

Quick Overview

Seniority
Mid Senior
Work mode
Hybrid
Location
McLean, VA, United States
Posted
Yesterday
MicroservicesGitHub ActionsLLMPlaywright

Job Description

Role - GenAI / Agentic Test Automation Engineer
Location -
Tysons, VA

Let’s create our future together at The AES Group!

About The AES Group:
The AES Group is a premier technology and engineering consulting company that has been bringing businesses and talent together for over 20 years to deliver innovative solutions that have the greatest positive impact on society. AES has helped over 40 business enterprises, including Fortune 500 companies, engage their customers, empower their employees, and transform their business operations with the power of cloud, data, AI, engineering, and other emerging technologies.

Job Description
We are seeking a GenAI / Agentic Test Automation Engineer with strong experience in LLM-powered agents, test automation, GitHub Copilot, GitHub Actions, Karate, and Playwright. The candidate will build reusable AI-driven testing solutions, quality gates, and reporting capabilities across microservices.

Key Responsibilities

  • Design and implement agentic testing frameworks for test generation, test maintenance, failure analysis, root-cause identification, and defect drafting.
  • Develop reusable testing patterns, reference implementations, templates, and standards across UI, API, integration, and contract testing.
  • Define test coverage standards, risk-based testing strategies, tagging/metadata, and test governance.
  • Build GenAI-powered reporting that aggregates test results, service health, logs, metrics, traces, and defect data across microservices.
  • Develop AI-driven insights for release readiness, failure clustering, trend analysis, and change/PR correlation.
  • Build automated AI quality gates to validate user stories, acceptance criteria, test data, dependencies, edge cases, and non-functional requirements.
  • Integrate quality gates and automation into GitHub Actions, pull requests, issue templates, and CI/CD workflows.

Required Skills

  • Hands-on experience building LLM-powered/agentic AI solutions, including prompting, structured outputs/JSON schemas, guardrails, evaluation, and hallucination reduction.
  • Strong experience with GitHub Copilot, GitHub Actions, CI/CD, GitHub APIs, PR checks, and branch protection.
  • Advanced Karate experience for API/contract testing and Playwright experience for UI automation.
  • Strong knowledge of test design, including positive, negative, edge/boundary, regression, test data, and test isolation strategies.
  • Experience working with microservices and aggregating test results across multiple pipelines.
  • Experience developing automated requirements validation and AI-assisted reporting solutions.

Key Deliverables

  • Reusable Agentic Test Automation Kit
  • Standardized test coverage guidelines and templates
  • GenAI-assisted reporting pipeline
  • Automated AI quality gates integrated with GitHub
  • Improved test coverage, reduced test maintenance, and reduced story churn/rework
 

Similar jobs