AI QA Trainer (AI)

TL;DR

AI QA Trainer (AI): Evaluating and hardening LLM reasoning, reliability, and safety with an accent on hallucination detection and adversarial red-teaming. Focus on designing test plans, building evaluation rubrics, and implementing automation for model verification.

Location: Remote

Salary: $6 - $65 per hour

Company

hirify.global focuses on developing enterprise-grade AI platforms by providing rigorous evaluation data to harden model reasoning and reliability.

What you will do

• Challenge advanced language models on hallucination detection, factual consistency, prompt-injection, and jailbreak resistance.
• Design and execute comprehensive test plans, regression suites, and clear pass/fail rubrics.
• Perform adversarial red-teaming and bias/fairness audits to ensure model safety and compliance.
• Capture reproducible error traces with root-cause hypotheses and suggest improvements to prompt engineering and guardrails.
• Collaborate on automation using Python and SQL to track quality deltas and evaluation metrics.

Requirements

• Bachelor's, Master's, or PhD in Computer Science, Data Science, Computational Linguistics, Statistics, or a related field.
• Proven experience shipping QA for ML/AI systems.
• Proficiency with test automation frameworks (e.g., PyTest) and LLM evaluation tooling (e.g., OpenAI Evals, RAG evaluators).
• Hands-on experience in adversarial testing, red-teaming, and grounding verification.
• Strong skills in prompt and system-prompt engineering.
• Ability to provide clear, metacognitive communication and detailed technical documentation.

Culture & Benefits

• Fully remote work arrangement.
• Freelance, project-based contract.
• Hourly pay range from $6 to $65, determined by experience and geographic location.
• Opportunity to contribute to the development of world-class AI education and research tools.