QA Engineer (AI)

TL;DR

QA Engineer (AI): Establishing the foundational quality strategy for AI-driven products and agentic workflows with an accent on automated testing, model evaluation, and system reliability. Focus on building autonomous testing agents, validating LLM outputs, and ensuring quality across complex financial and security-critical flows.

Location: Ukraine

Company

hirify.global is a technology company building advanced AI-driven products and agentic platforms.

What you will do

• Own the end-to-end testing strategy, determining the balance between manual, automated, and AI-agent-driven testing.
• Build and maintain end-to-end automation suites using Playwright, Cypress, or Selenium.
• Develop and maintain Day and Night testing agents to autonomously run suites, analyze results, and manage tickets.
• Perform specialized AI testing, including hallucination detection, prompt injection, RAG retrieval quality, and jailbreak resistance.
• Define and operate benchmarks for models and agents to track quality metrics over time.
• Collaborate with internal engineers and stakeholders to set production quality gates and manage the full bug lifecycle.

Requirements

• Minimum 4 years of QA experience with at least 2 years of end-to-end ownership.
• Strong proficiency in manual testing fundamentals and hands-on experience with Playwright, Cypress, or Selenium.
• Experience with API testing (REST/GraphQL) and strong SQL skills (PostgreSQL/MySQL).
• Advanced proficiency in Hebrew (native or near-native) and professional English.
• Demonstrated ability to work with LLMs, prompt engineering, and AI failure modes.
• Scripting proficiency in Python for API interaction and data validation.

Nice to have

• Experience testing LLM/GenAI products in production environments.
• Familiarity with RAG, vector databases, and multi-agent systems.
• Background in security testing (OWASP Top 10) or performance testing.
• Knowledge of Model Context Protocol (MCP) and agent frameworks.

Culture & Benefits

• Work in a highly autonomous environment with no embedded mentoring.
• Utilize advanced AI-agent workflows for daily tasks and iteration.
• Direct impact on the foundational quality posture of the AI department.
• Opportunity to define and implement cutting-edge AI testing methodologies.