AI Safety Testing Associate (Remote - Worldwide)
The posting does not state country restrictions. This is a safety testing role with an expert network that supports AI model evaluation projects. You will look for ways AI systems can fail and document your findings so model developers can improve safety. Projects are fully remote and matched to your background.
What you'll do
- Write single-turn prompts and multi-turn conversations that test whether models can be pushed past safety guidelines.
- Test known and new jailbreak techniques and record which approaches succeed or fail.
- Assess whether models follow unintended instructions embedded in documents or tool outputs.
- Evaluate whether models with access to tools such as code execution, browsers, or email can be steered into harmful actions.
- Compare model responses across demographic groups, names, and languages to identify potential bias.
- Audit model answers against written safety policies, flag violations, and label content as safe or unsafe.
What you need
- Zero to five years of professional experience. Prior AI data work is not required.
- Experience testing systems or software by trying to break them and documenting steps and results.
- Experience applying written policies or guidelines to evaluate content or behavior.
- Background in one or more areas such as security testing, CTFs, trust and safety, content moderation, policy analysis, fairness research, adversarial machine learning, QA testing, or cyber, bio, or chemical expertise.
- Clear written English and meticulous documentation habits. Ability to work with sensitive content under structured guidelines.
- Familiarity with jailbreaks, prompt injection, or LLM red teaming is helpful, as is experience with tools such as Burp Suite, Garak, or PyRIT.
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
RL Environment and Agent Evaluation Specialist (Remote - Worldwide)
Pay: $35/hr - $70/hr (hourly rate). Open to applicants in any country; project-based work with flexible hours. This is a paid talent pool for an AI company working on AI agents and reinforcement learning. Contributors he…
AI Response Evaluation and Feedback Associate (Remote - Worldwide)
Fully remote, no country restriction stated. Paid for hours worked. A project-based expert network that supports the evaluation and improvement of AI models. Contributors give structured feedback that helps model respons…
AI Data Annotation Specialist (Remote - Worldwide)
Pay: $40/hr - $75/hr (hourly rate). This is an expert-level data annotation role supporting advanced AI research teams. You will work on complex, multimodal datasets, take on the hardest and most ambiguous cases, and hel…
AI Evaluation Specialist, Contract Talent Pool (Remote - Worldwide)
Pay: $30/hr - $60/hr (hourly rate). This is a contract position in a specialist talent pool that supports human-data projects evaluating AI models. Contributors design and run assessments that measure what models can and…
Senior Software Engineer I/II, Operational AI (Remote - US and Canada)
This is a senior engineering role on the Operational AI team at a public company that builds connected operations software for industries such as transportation, construction, agriculture and field services. The team tur…
Related job searches
Remote AI JobsAI jobsEntry-Level jobsWork From Home jobs in NigeriaWork From Home jobs