$15-75/hrAs published by the platform.
This role involves red-teaming and security testing of AI models to identify vulnerabilities and safety issues before deployment. The position is ideal for cybersecurity professionals who want to apply adversarial thinking and penetration testing skills to AI systems used at scale.
$15-75/hr
Pay as published by the platform. It is not a guarantee of income or hours.
The platform has not published which countries are eligible for this job.
You apply on Alignerr, Labelbox's expert network: create a profile, complete an AI-led interview and skills assessment, then get matched to projects in your field.
Official posting: https://www.alignerr.com/jobs/01f2ff84-0a4a-4d87-bcce-ca482595621c
Last checked on October 8, 2026.
This role involves analyzing security vulnerabilities and threat scenarios in AI systems and large language models to identify weaknesses and recommend mitigations. Security professionals will conduct adversarial testing, evaluate real-world attack scenarios, and provide structured feedback to improve AI safety and resilience.
Penetration testing experts are needed to identify security vulnerabilities in AI-powered applications and infrastructure through offensive security testing. This remote contract role combines traditional penetration testing methodologies with emerging AI-specific attack scenarios such as prompt injection and model manipulation.
You join a red teaming team specialized in adversarial evaluation of conversational AI models. Your role consists of testing AI systems by exploring their vulnerabilities (jailbreaks, prompt injections, biases), generating high-quality data documenting these vulnerabilities, and producing reproducible reports to strengthen model safety. This position is for bilingual English-Danish experts with prior experience in red teaming or related fields (cybersecurity, adversarial ML, socio-technical analysis).
Posted July 30, 2026
This role involves stress-testing frontier AI models with adversarial prompts to uncover jailbreaks, unsafe behaviour and policy failures on sensitive topics. It is aimed at experienced safety, security, life sciences or policy professionals who can document weaknesses and help researchers strengthen model alignment.
Posted July 16, 2026
This role involves evaluating how AI models reason about offensive security concepts and identifying flaws in their exploit chain reasoning. Penetration testers with hands-on red team experience will test model outputs across reconnaissance, exploitation, privilege escalation, and lateral movement, then write accurate attack paths that reflect real-world tradecraft when models fall short.
You will evaluate AI-generated code by running models on real engineering tasks, analyzing their output against production standards, and stress-testing them to find failures. This role is ideal for experienced software engineers who want to contribute to AI model improvement through rigorous code review and red-teaming.
