Haystack
← Back to Jobs
Technology
TR

Test Automation Engg - Test Architect - Agentic AI

Trispark IncCoppell, TX🇺🇸United StatesPosted 10 Sept 2026

Quick Overview

Seniority
Mid Senior
Work mode
Hybrid
Location
Coppell, TX, United States
Posted
22 hours ago
SeleniumAzureC#CypressGitHub ActionsJavaJavaScriptJenkinsLLMPlaywrightPostmanPythonRESTTypeScriptpytest

Job Description

JD for Lead Software Test Automation Architect | Agentic AI:

We are seeking a Lead Test Automation Architect to define and lead an enterprise-grade test automation strategy across UI, API, data, and platform layers—while evolving our quality engineering capabilities to support Agentic AI / LLM-based systems (probabilistic outputs, confidence-based validation, hallucination detection, and model evaluation). This role will architect scalable automation frameworks, drive engineering excellence, and accelerate delivery through highly productive, maintainable automation programs.



Key Responsibilities

Automation Strategy & Architecture

  • Define and own the test automation architecture and multi-layer strategy (UI/API/contract/integration/e2e), aligned to product risk and release cadence.
  • Establish automation standards, patterns, and reference implementations (framework structure, page-object/screenplay usage, test data patterns, reporting).
  • Drive shift-left testing practices (contract testing, component testing, pre-merge validation) and reduce reliance on fragile end-to-end tests.

Agentic AI / LLM Test Model Alignment

  • Design and implement testing approaches for non-deterministic AI outputs, including:
    • confidence/threshold-based assertions
    • semantic similarity checks and rubric-based validation
    • goldens/benchmark datasets and evaluation harnesses
    • hallucination and groundedness testing strategies
    • regression detection across model/prompt/version changes
  • Define AI test coverage across accuracy, robustness, bias/safety (as applicable), performance, and reliability.
  • Partner with ML/AI, Product, and Engineering to establish acceptance criteria for AI capabilities and measurable quality gates.

High-Productivity Automation Programs

  • Build and scale high-throughput automation projects that are reliable, fast, and easy to extend.
  • Improve test execution time, reduce flaky tests, and optimize CI/CD pipelines (parallelization, test selection, retries with guardrails).
  • Create actionable, engineering-friendly quality dashboards (pass/fail trends, flake rate, coverage, defect escape metrics).

Tooling, CI/CD, and Quality Gates

  • Integrate automation into CI/CD with quality gates (PR checks, nightly suites, release readiness criteria).
  • Standardize observability for testing: logs, tracing hooks, screenshots/video, artifacts, and test run diagnostics.
  • Define practices for test environments, data management, service virtualization, and dependency control.

Technical Leadership & Mentorship

  • Serve as the QE technical authority: coach engineers on automation design, code quality, and best practices.
  • Lead design reviews for test architecture and automation PRs; enforce coding standards and maintainability.
  • Influence roadmap and delivery by translating risk into clear testing priorities.

Required Qualifications

  • 8–12+ years in Quality Engineering / Test Automation with architect-level ownership of frameworks and strategy.
  • Proven experience designing scalable automation across:
    • API testing (contract + integration)
    • UI automation with stable locator strategies (test IDs, accessibility roles)
    • Test data strategy and environment reliability
  • Strong programming skills in at least one modern language (e.g., Java, Python, TypeScript/JavaScript, C#).
  • Expertise with automation tools/frameworks (examples):
    • UI: Playwright / Cypress / Selenium
    • API: REST-assured / SuperTest / Postman/Newman / pytest
    • CI: GitHub Actions / Jenkins / Azure DevOps
  • Demonstrated ability to reduce flakiness and improve execution speed through engineering solutions.

Preferred Qualifications (Strongly Desired)

  • Experience testing LLM/Agentic AI features or other probabilistic systems, including:
    • evaluation harnesses, benchmark datasets, semantic scoring, and drift detection
    • prompt/version regression strategies and structured evaluation reports
  • Familiarity with modern quality approaches: test pyramid, contract testing, consumer-driven contracts, risk-based testing, shift-left.
  • Knowledge of security/performance testing integration (baseline understanding; hands-on is a plus).
  • Experience building reusable automation libraries for multiple teams/products.

Similar jobs