AI SDET / AI Evaluation Engineer

Job ID GT-1080

About the role

We are seeking an experienced SDET / QA Automation Engineer to test and evaluate enterprise AI applications in the legal technology space. You will use AI coding agents to build automated test suites, evaluate LLM responses for accuracy and retrieval relevance, and help ensure the quality of AI-driven workflows and integrations.

Responsibilities

Build and execute automated tests for enterprise AI applications using AI coding agents
Evaluate AI responses for accuracy, completeness, citations and retrieval relevance
Maintain test datasets and regression suites
Investigate AI application failures and identify root causes
Test APIs, document ingestion, AI workflows and integrations
Compare AI model and application versions and report evaluation results

What happens after you apply

A recruiter reviews your application within two business days. If your experience and rate line up, we call you before submitting you anywhere — your profile is never sent to a client without your say-so.