Red Teaming AI training jobs

Offensive Security Analyst

• Software Engineering
• Platform: Alignerr
• Level: Intermediate

This remote contract role asks analysts to bring offensive security knowledge to AI development without writing exploits or taking part in live intrusions. The work centers on analyzing attack paths and adversary behavior in structured scenarios, then producing labeled reasoning data and written assessments that help AI systems reason about cybersecurity. It suits experienced security professionals who can explain how real attacks unfold in production environments.

OpenClaw Security Expert & Power User

• Data & Machine Learning
• Platform: Alignerr

This contract role asks security-minded people to probe AI systems built on the OpenClaw platform by running red-teaming exercises and writing adversarial prompts. The work suits cybersecurity practitioners who enjoy finding weaknesses and who can document their findings clearly for technical and non-technical readers.

Statistics Expert

• Science & Research
• Platform: Alignerr

This remote, asynchronous role involves labeling and organizing statistical content, such as equations, datasets and problems, to build training data for AI systems. It also includes reviewing AI-generated statistics solutions, writing instructional material and testing models for reasoning errors and bias. It is aimed at people with strong probability and statistics backgrounds from research, teaching or applied work.

Penetration Tester

• Software Engineering
• Platform: DataAnnotation

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.

Software Engineer

• Software Engineering
• Platform: DataAnnotation

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.

Behavioral Health Expert, AI Safety and Model Evaluation

• Health & Medicine
• Platform: Mercor
• Location: United States
• Level: Intermediate

This role involves evaluating and improving how AI models respond to sensitive conversations about relationships, emotional well-being, and personal beliefs. You will analyze whether the model's responses remain balanced, neutral, and safe, and you will help researchers define quality standards. This role is suited for professionals from mental health, counseling, or social work who can clearly articulate why one response is better than another.

Posted October 2, 2026

Cybersecurity Practitioner: Paid Expert Interviews (SOC, Incident Response, Detection, AppSec)

• Software Engineering
• Platform: Mercor
• Location: United States

Mercor is recruiting operational cybersecurity experts to participate in video research interviews designed to create a benchmark of AI agents in enterprise defense. This short, well-paid job involves sharing your practical experience on tools, decision-making processes, and the potential impact of AI in your field.

Posted September 23, 2026

Senior AI Trainer

• Data & Machine Learning
• Platform: micro1
• Location: 58 countries

You are invited to contribute as a senior AI trainer to a client project aimed at improving the quality of AI systems. You will evaluate AI-based chat and search tools, refine prompts to test model capabilities, and provide structured feedback to optimize their performance. This role is suited for professionals with proven experience in AI model training and data annotation.

Posted September 23, 2026

Management Consulting Expert

• Business, Consulting & Operations
• Platform: Mercor
• Location: United States

Consulting role where you will evaluate and assess the capabilities of AI models on real-world strategy, operations, or transformation cases. You will write case statements based on your experience, evaluate market analyses and recommendations generated by AI, and flag answers that are overly polished to withstand rigorous scrutiny. Intended for experienced consultants who wish to contribute to AI training.

Posted September 15, 2026

Analytical Chemist

• Science & Research
• Platform: Mercor
• Location: United States

You will write test prompts to evaluate whether AI models can distinguish legitimate chemical requests from potentially dangerous misuses. As an analytical chemist, you will develop scenarios along the dual-use line, assess model responses against a defined policy, and document your analyses with accessible technical reasoning.

Posted September 14, 2026

Chemical Defense Researcher

• Science & Research
• Platform: Mercor
• Location: United States

You will work on evaluating frontier AI models to test their ability to distinguish legitimate chemical requests from malicious uses. As a chemical defense researcher, you will write targeted questions, evaluate model responses against a defined policy framework, and document your judgments with rigorous technical justifications. This role requires deep expertise in chemical defense to draw the line between routine professional questions and those with high potential for misuse.

Posted September 14, 2026

Commercial Blasting Engineer

• Engineering
• Platform: Mercor
• Location: United States

You will contribute to evaluating AI models as an expert in explosives and energetic materials. Your role involves writing sharp technical questions in your field, evaluating model responses against a safety policy, and documenting correct answers with technical justification. This work requires the ability to distinguish legitimate professional questions from suspicious requests that could serve malicious purposes.

Posted September 14, 2026

Emergency Response Specialist

• Science & Research
• Platform: Mercor
• Location: United States

You will contribute to evaluating AI models for radiological safety by writing test requests at different difficulty levels and judging whether the model's responses meet safety standards. This role requires recognized expertise in radiological crisis management, capable of distinguishing legitimate professional questions from potentially dangerous requests.

Posted September 14, 2026

Federal Certified Materials Specialist / Incident Analyst

• Science & Research
• Platform: Mercor
• Location: United States

You will write and evaluate requests designed to test the ability of AI models to distinguish legitimate technical questions from dangerous requests in the field of energetic materials. This role requires deep expertise in post-incident analysis and regulatory inspection to draw the line between routine professional uses and potential misuse.

Posted September 14, 2026

Forensic Scientist - Nuclear Materials

• Science & Research
• Platform: Mercor
• Location: United States

You will contribute to the evaluation of frontier AI models as an expert in nuclear materials and non-proliferation measures. Your job is to write sophisticated test questions in your field and evaluate whether models correctly refuse dangerous requests while answering legitimate questions, drawing a subtle line between civil and military applications.

Posted September 14, 2026

Forensic / Toxicological Chemist

• Health & Medicine
• Platform: Mercor
• Location: United States

You will join a team of chemistry and chemical safety experts tasked with testing the capabilities of frontier AI models to assess risks of misuse of legitimate purposes. Drawing on your expertise in forensic chemistry or toxicology, you will write sophisticated test questions, evaluate model responses against defined policy criteria, and develop reference answers with technical justifications.

Posted September 14, 2026

Hazardous Device Specialist / Public Safety Professional

• Science & Research
• Platform: Mercor
• Location: United States

This role involves assessing the ability of AI models to correctly judge the potential for misuse of technical requests concerning energetic materials and propulsion. As a specialist, you will write progressively complex questions, evaluate model responses against a defined policy, and document your analyses to guide the behavior of AI systems when facing real-world risks.

Posted September 14, 2026

Health Physicist

• Health & Medicine
• Platform: Mercor
• Location: United States

You will help test the robustness of AI models against malicious risks as a radiation protection specialist. Your role consists of designing deliberately ambiguous technical requests, evaluating the model's responses according to a defined security policy, and documenting best practices, while knowing how to distinguish legitimate professional questions from malicious intentions.

Posted September 14, 2026

Industrial Hygienist / Process Safety Engineer

• Health & Medicine
• Platform: Mercor
• Location: United States

You will evaluate how AI models handle sensitive requests in industrial hygiene and process safety, distinguishing legitimate professional questions from malicious bypass attempts. You will write graduated test requests, assess model responses against a defined policy standard, and document your judgments with technical reasoning accessible to non-specialists. This role is for experienced practitioners who have evaluated real exposures and process risks in professional settings.

Posted September 14, 2026

Nonproliferation Analyst

• Legal
• Platform: Mercor
• Location: United States

You will write and evaluate test cases to verify that an AI model knows how to refuse dangerous requests while answering legitimate questions in the field of nuclear nonproliferation. This role requires professional expertise in export controls, treaty implementation, or nuclear program analysis, so you can draw the line between routine compliance questions and circumvention attempts.

Posted September 14, 2026