Expert Talent Pool, Safety Testing Associate

Expert Talent Pool

WorldwideFully remoteFull TimeEntry Level, Junior, Mid LevelInformation Technology
USD 30–60 an hourPosted 13h ago

Why we think you can apply

Hiring model
Open worldwide · the employer states no country restriction
Work from
Anywhere, the UAE included

Posted 13 hours ago · apply link checked 5 hours ago

About the role

Responsibilities

  • Write prompts and multi-turn conversations testing model adherence to safety guidelines
  • Try known and novel jailbreak techniques and record outcomes
  • Test for prompt injection using hidden instructions in documents and tool outputs
  • Evaluate whether tool-using models can be manipulated into harmful actions
  • Compare responses across demographic groups, names and languages to identify bias
  • Review model responses against written safety policies and flag violations
  • Label content as safe or unsafe per project guidelines

Requirements

  • 0 to 5 years of professional experience
  • Security testing, CTFs, trust and safety, content moderation or policy analysis experience
  • Experience testing systems or models by trying to break them and documenting results
  • Experience applying written policies or guidelines to label content or behavior
  • Strong written English and careful documentation habits
  • Ability to work with sensitive content under structured guidelines

Preferred Qualifications

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

Benefits

  • Compensation of $30 to $60 per hour, based on hours worked

About the Company

An expert network supporting AI model evaluation projects, matching experts to projects by background.

What we look for

  • 0 to 5 years of professional experience
  • Security testing, CTFs, trust and safety, content moderation or policy analysis experience
  • Experience testing systems or models by trying to break them and documenting results
  • Experience applying written policies or guidelines to label content or behavior
  • Strong written English and careful documentation habits
  • Ability to work with sensitive content under structured guidelines
  • Familiarity with language model jailbreaks, prompt injection or red teaming
  • Familiarity with Burp Suite, Garak, PyRIT or the OWASP LLM Top 10
SecurityQuality AssuranceContent ModerationRed TeamingBurp SuitePrompt InjectionGarakPyRITOWASP LLM Top 10Trust and Safety
NeverApplySponsor

Wake up to a shortlist, not a search results page.

NeverApply scores every new listing against your CV, salary floor and visa. A handful of real matches by morning.

Get your daily matches
Similar jobsbased on title, category and scope
Expert Talent Pool, Safety Testing Associatefree account, 30 seconds

Every new role, on Telegram.

Members see each new UAE role first. A day later it lands in the channel, where 6,800 people follow.

FreeNo spamUpdated hourly
Or show me jobs that hire in the UAE

Remote Jobs in Dubai UAE

6,800+ followers

Get alerts on Telegram