Safety Testing Associate

Responsibilities

• Write prompts and multi-turn conversations testing whether models can be pushed past safety guidelines
• Test known and novel jailbreak techniques, recording which succeed or fail
• Assess whether models follow unintended directives embedded in documents and tool outputs
• Evaluate whether models with tool access can be manipulated into harmful actions
• Compare model responses across demographic groups, names and languages to identify bias
• Audit model answers against written safety policies and flag violations
• Label content as safe or unsafe according to established guidelines

Requirements

• Zero to five years of professional experience
• Experience testing software, systems or models by attempting to break them
• Experience applying written policies or guidelines to evaluate content or behavior
• Background in security testing, trust and safety, content moderation, policy analysis, fairness research, QA or related domains
• Clear written English and meticulous documentation habits
• Ability to work with sensitive content under structured guidelines

Preferred Qualifications

• Familiarity with jailbreaks, prompt injection or red teaming language models
• Experience with Burp Suite, Garak, PyRIT or knowledge of the OWASP LLM Top 10

Benefits

• Compensation of $30 to $60 per hour, depending on project, field and experience, paid by hours worked
• Fully remote, project-matched work