Job

Expert Talent Pool, Safety Testing Associate

Clera Clera offers roles in legal evaluation of AI systems and ML internship opportunities

Remote mid-level safety testing role evaluating AI model safety, with hourly pay of $30–$60.

Open to Rwandans

At a glance

Deadline
Location
Remote
Salary
30 – 60 USD / hour
Paid
Yes
Employment type
Full Time
Listed

About this opportunity

Clera is seeking a mid-level safety tester to join its expert network for AI model evaluation projects. This fully remote, full-time role focuses on identifying how AI systems can fail and documenting findings to improve model safety across projects.

You will write prompts and multi-turn conversations to test model adherence to safety guidelines, attempt jailbreak techniques, test for prompt injection, and assess bias across demographic groups, languages, and names.

The job emphasizes careful documentation, adherence to project guidelines, and strong written English. It welcomes candidates with experience in security testing, trust and safety, content moderation, policy analysis, fairness research, or related fields, and also values curiosity about how systems can be challenged.

Key steps include matching you to suitable projects, conducting tests, recording results, and reporting violations or safe/unsafe classifications. Time zones span globally, with fully remote work and hourly compensation.

What you get

  • Hourly compensation of $30 to $60
  • Fully remote work
  • Project-based, hourly pay
  • Opportunity to work on AI safety and bias testing projects

Responsibilities

  • Write prompts and multi-turn conversations to test model safety.
  • Try jailbreak techniques and document success or failure.
  • Test for prompt injection using hidden instructions in documents and tool outputs.
  • Evaluate model interactions using tools like code, browsers, or email for potential misuse.
  • Compare responses across demographics, languages, and names to identify bias.
  • Review model outputs against safety policies and flag violations.
  • Label content as safe or unsafe per project guidelines.

Requirements

  • 0 to 5 years of professional experience
  • Experience in security testing, trust and safety, content moderation, policy analysis, fairness or bias research, or adversarial ML is useful
  • Experience testing software, systems, or models by attempting to break them and documenting results
  • Strong written English and careful documentation habits
  • Familiarity with language model jailbreaks, prompt injection, or red teaming is useful
  • Familiarity with Burp Suite, Garak, PyRIT, or OWASP LLM Top 10 is useful

How to apply

  • Apply via the linked listing on Himalayas.app or the posting page.
  • Ensure your experience aligns with the described responsibilities and skills.

Ready to apply?

57days left
Deadline
Apply on the official site

WorkInRwanda never asks for money to apply. If anyone does, report it. Report this listing

About Clera

Clera is involved in legal and artificial intelligence work, offering roles that blend EU law expertise with AI evaluation. The listings indicate remote opportunities available worldwide and focus on senior legal professionals with EU knowledge as well as entry-level ML work.

See everything from Clera
57 days left Apply