AI Safety Red Team Expert (Remote - Worldwide)
Projects run from one week to several months. This is an expert pool for an AI company that supports safety testing projects for AI systems. Members are matched to projects and lead evaluations covering security, fairness, and domain-specific safety. The work aims to find and address risks before AI systems are released. Compensation is $75 to $175 per hour, depending on project, field, and experience, and is paid for hours worked.
What you'll do
- Design and lead red teaming campaigns that probe high-risk model capabilities for attack vectors.
- Develop jailbreak techniques and document them so they can be reproduced and shared.
- Test agent systems for prompt injection through untrusted inputs, and probe tool-enabled models (code execution, browsing, messaging) for misuse.
- Design bias testing frameworks and assess fairness across demographic groups and languages.
- Audit model behavior against written safety policies, rate findings by severity, and recommend fixes.
- Write moderation guidelines, resolve edge cases, and review the work of other testers or moderators.
What you need
- At least five years of experience in security testing, trust and safety, policy, fairness research, adversarial machine learning, or a closely related area such as cyber, biological, chemical, or child safety.
- Hands-on AI safety testing experience, including red teaming, jailbreaks, prompt injection, or tool misuse.
- Experience designing test plans, threat models, or audits that others have carried out, and experience leading or reviewing testers or moderators.
- Familiarity with tools such as Burp Suite, Garak, or PyRIT, or knowledge of the OWASP LLM Top 10.
- Strong written English and the ability to work with sensitive content within ethical guidelines.
Open to applicants anywhere in the world.
How to apply
Get the free i'llTip app to see the employer's details and apply. i'llTip's AI can tailor your résumé to this job, and you'll get alerts for similar roles.
Apply on i'llTipPrefer the website? Continue on illtip.comOr get the app: Android · iPhone
🔔 Get new jobs like this first: join Tech & AI Jobs on Telegram · or get personal job alerts
More Cybersecurity & Data Protection jobs
Information Security Engineer, Application Security (Remote - Worldwide)
Open to candidates anywhere; hiring is through a global employer partner where you are not in a main office market. A fast-growing enterprise software company that sells workflow and process orchestration software to lar…
Senior Exposure Management Engineer (Remote - US only, Mid-Atlantic)
Applicants must be legally authorized to work in the US without current or future visa sponsorship. Some travel (up to 10%) may be required. This is a senior engineering role within a Mid-Atlantic exposure management pra…
Security Engineer (Remote - Worldwide)
The posting does not list country eligibility. Pay is in USD and the work supports national security and civilian missions, so confirm any work-authorization or citizenship requirements on the employer's page before appl…
Senior Technical Data Security Architect (Remote - US only)
A fast-growing, privately held cybersecurity services firm is hiring a senior architect to design and govern data security across cloud data platforms. The role sits on a central data platform team and acts as the lead t…
Related job searches
Remote AI JobsAI jobsContract jobsWork From Home jobs in NigeriaWork From Home jobs