AI Safety Testing Associate (Remote - Worldwide)
Pay: $30/hr - $60/hr (hourly rate). The posting does not restrict eligibility by country. This is an expert talent pool supporting AI model evaluation projects. Members are matched to safety testing work based on their background, and pay depends on the project, subject area and experience. The work is about finding and documenting the ways AI systems can fail so that their safety can be improved. Prior AI data work is not required.
What you'll do
- Write single prompts and multi-turn conversations that test whether AI models follow safety guidelines.
- Attempt known and new jailbreak methods and record which ones succeed or fail.
- Plant hidden instructions in documents and tool outputs to test for prompt injection weaknesses.
- Check whether models that use tools such as code execution, browsers or email can be pushed into harmful actions.
- Compare model responses across demographic groups, names and languages to spot potential bias.
- Review outputs against written safety policies, flag violations and label content as safe or unsafe.
What you need
- 0 to 5 years of professional experience. Experience in security testing, CTF competitions, trust and safety, content moderation, policy analysis, fairness research, adversarial machine learning, QA, or a relevant cyber, bio or chemical domain.
- Experience testing software, systems or models by trying to break them and documenting steps and results.
- Experience applying written policies or guidelines to judge content or behavior.
- Familiarity with language model jailbreaks, prompt injection or red teaming is useful, as are tools such as Burp Suite, Garak or PyRIT, or the OWASP LLM Top 10.
- Strong written English and careful documentation habits, with the ability to handle sensitive content under structured 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 AI & Machine Learning jobs
AI Evaluation Associate (Remote - Worldwide)
Pay: $30/hr - $60/hr (hourly rate). This is a remote role with a company that runs human-led evaluations of AI models. You will help measure what models can and cannot do by writing rigorous test questions, building scor…
Physical AI Data Collection Associate (Remote - Worldwide)
Pay: $20/hr - $40/hr (hourly rate). Some on-site projects are also offered. This is a data-collection role supporting a physical AI network that runs paid projects to help train embodied AI systems. You will record real-…
Founding Harness Engineer, AI Agent Runtime (Remote - Eastern Europe)
Working-hour overlap with the team is still to be confirmed. This is a founding engineering role at an early-stage AI company building an AI coworker product for team workplaces. You will own the runtime that lets an AI …
Lead Engineer, AI Platform (Remote - EMEA)
A fast-growing advertising technology company that uses generative AI to help brands and small businesses produce creative content is hiring a hands-on technical lead for the platform that runs its AI agents. The product…
Related job searches
Remote AI JobsAI jobsEntry-Level jobsWork From Home jobs in NigeriaWork From Home jobs