Careers

Careers

Careers

QA Test Automation & AI Evaluation Engineer

Full Time

Remote / Hybrid

4 years+

Aug 5, 2026

About Candle AI

Candle AI is a fast-growing legal-tech startup based in Austin, TX. Our AI-agents for legal emails integrates directly into Gmail & Outlook. Our mission is to revolutionize how high-volume professional services firms like law firms manage their client communications, save hours of billable time, and unlock additional revenue.

Backed by prominent investors like The Legal Tech Fund (TLTF) and with a growing pipeline of law firms & trusted early design partners, Candle AI is on track to become the status quo in legal email efficiency.

The role

You'll own our test automation and AI evaluation frameworks end to end, across our extension, add-in, and API surfaces. There's no QA team to inherit: you decide what quality means here and build the machinery that proves it.

What you'll do

  • Own and extend our Playwright-based automation framework, including test data, environments, and CI integration.

  • Build and run our AI evaluation framework — eval sets and scoring criteria that catch quality regressions in AI output release over release.

  • Use agentic AI coding tools and MCP-based workflows to generate and maintain tests at the pace we ship.

  • Keep the suite trustworthy: triage failures, kill flakiness, and report the quality signals we make release decisions on.

  • Explore by hand where automation can't reach — integration failure modes, cross-client rendering, and AI behavior that needs human judgment.

What we're looking for

  • 4+ years in QA, SDET, or test engineering for SaaS or web applications, including a suite you owned.

  • Strong Playwright (or equivalent modern E2E framework) and comfort in TypeScript/JavaScript.

  • Real fluency with agentic AI coding tools applied to test creation and maintenance.

  • Working knowledge of REST APIs and OAuth flows.

  • A self-starter who sets their own roadmap and ships without being managed.

Bonus points

  • Experience with LLM evaluation — eval sets, LLM-as-judge, regression scoring.

  • CI/CD (GitHub Actions or similar), with automation wired into the development loop.

  • Browser extension, Outlook Add-in, or Office 365 testing.

  • Early-stage startup, productivity tooling, or legal tech.

How to apply

To Apply: Send your resume to careers@candle.ai

Copyright © 2026 Candle AI, Inc.

All rights reserved.

Copyright © 2026 Candle AI, Inc.

All rights reserved.