Remote AI Safety Red Team Specialist

Mercor is assembling a remote AI red team to proactively probe AI models with adversarial inputs, assess vulnerabilities, and generate actionable data for safer customer AI systems. You will work on high-sensitivity topics with clear guidelines and wellness resources; participation in certain projects is optional. Strong English and Swedish language...

Join Mercor as a Remote AI Red Team Specialist focused on enhancing AI safety. Utilize your skills in red teaming conversational models and generating human data to identify and address vulnerabilities.As a specialist with Mercor, you will work on adversarial inputs for AI models while collaborating with a team of data experts. Your focus will be on...

Mercor is building a dedicated team to red-team frontier AI models by crafting challenging prompts and evaluating AI responses. The work centers on distinguishing legitimate questions from dangerous ones, while maintaining rigorous documentation. Ideal candidates have hands-on casework in chemistry or toxicology and can write clear, justified analyses for...

Mercor in Toronto is assembling a panel of radiological safety experts to red-team frontier AI models. The role focuses on writing prompts across benign, dual-use, and adversarial levels, and evaluating model responses against a policy standard. You will also draft reference answers with the technical reasoning, and contribute to training materials. Prior...

Location Remote Fluent Language Skills Required English & Punjabi. Native fluency in English and Punjabi is required for this position. Why This Role Exists At Mercor, we believe the safest AI is the one that’s already been attacked — by us. We are assembling a red team for this project - human data experts who probe AI models with adversarial...

Alignerr is seeking an AI Red Team Penetration Tester to rigorously test AI-powered applications and infrastructure. This remote, hourly contract role emphasizes offensive security expertise to uncover vulnerabilities before adversaries do. You will assess AI/ML pipelines, web, network, and API security, document findings clearly, and contribute to enhancing...

Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request—answering legitimate questions fully while refusing genuinely dangerous ones. You will write prompts at three levels (benign, dual-use, adversarial), evaluate model...

Mercor is assembling a panel of radiological safety experts to red-team frontier AI models. The goal is to test whether a model can correctly judge the misuse potential of a technical request—answering legitimate questions fully while refusing genuinely dangerous ones. You will write prompts at three levels (benign, dual-use, adversarial), evaluate model...

TELUS Digital AI Community invites an AI Safety & Policy Expert to join as an independent contractor. You will label and mitigate risks in training data, applying safety rubrics to thousands of scenarios, ensuring the model learns what is right and what is wrong.You’ll classify harmful content, verify facts, apply guidelines to edge cases, and feed...