AI Model QA Engineer: Graph Theory & Red Teaming

DataAnnotation; Wyoming; Remote; USD 124,000 - 207,000; Full time

Benefits offered by this job

Flexible, remote work

Job summary

DataAnnotation is seeking contributors to run agentic coding sessions on real engineering tasks, analyze what the models produce, and red-team them until they fail in interesting ways. Each failure you document improves the next generation of coding agents.

You will work remotely with flexible scheduling, documenting reasoning and results to help scale safe, capable AI systems. This role rewards precise explanations and rigorous testing.

Qualifications

• Professional or serious open-source experience shipping production code.
• Clear written English for explanations and documentation.
• No degree required; focus on ability and demonstrated work.

Responsibilities

• Vibe-code with frontier models on real tasks: fix bugs, extend APIs, ship features.
• Analyze the AI's work against production standards, identify bugs, explain failures.
• Red-team the models to expose unsafe code and confidently wrong solutions before users.

Skills

Open-source experience

Production code experience

Clear written English

Job description

DataAnnotation is seeking contributors to run agentic coding sessions on real engineering tasks, analyze what the models produce, and red-team them until they fail in interesting ways. Each failure you document improves the next generation of coding agents.

You will work remotely with flexible scheduling, documenting reasoning and results to help scale safe, capable AI systems. This role rewards precise explanations and rigorous testing.