Skip to content

Agentic & RL Envs

AI Jailbreak And Prompt-Injection Security Expert

The middle of its range, $70/hr, is above the $60/hr median of the Agentic Tasks & RL Environments roles open now, whose typical pay runs $50–$120/hr. How that pay moves week by week is in our research on Agentic Tasks & RL Environments work.

Half of all Agentic Tasks & RL Environments roles come down within 9.3 days of being listed, and 34.1% are still up after four weeks. This one was posted 18 days ago.

About the role

The work

You will evaluate how AI systems respond to adversarial requests and identify ways their safeguards can fail. The work combines hands-on security testing with clear reports and practical recommendations for improving model safety.

  • Design methods for testing jailbreaks, prompt injection, and tool-use abuse.
  • Create cross-domain strategies that uncover complex, multi-turn bypass patterns.
  • Build and maintain regression tests for jailbreak and prompt-injection vulnerabilities.
  • Develop evaluation frameworks based on realistic adversarial threats.
  • Turn security findings into model-safety and risk-mitigation recommendations.
  • Document methods, findings, and best practices for technical and non-technical audiences.

What it pays and takes

This is a part-time contractor role for someone with relevant AI security or model evaluation experience.

  • Pay: $50 to $90 per hour.
  • Location: Open to candidates in AE, AR, AT, BD, BE, BH, BR, CA, CH, CL, CO, DE, DK, DZ, EG, ES, FR, GB, GH, GR, ID, IN, IT, JO, JP, KE, KG, KW, KZ, LB, LK, MA, MX, MY, NG, NL, OM, PE, PH, PK, PS, PT, QA, SA, SG, TH, TN, TW, US, UZ, VN, and ZA.
  • Language: Professional fluency in English.
  • Experience: At least two years in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security field.
  • Required knowledge: Experience researching or testing jailbreaks, prompt injection, tool-use abuse, or adversarial AI attacks.
  • Useful skills: Understanding of current LLM architectures, prompt engineering, and security assessment practices, plus strong written and verbal communication.
  • Helpful background: An advanced degree in computer science, cybersecurity, machine learning, or a related discipline, or equivalent professional or operational experience.
  • Additional indicators: Published research, open-source security tools, conference presentations, or participation in multidisciplinary AI safety work.

How it works

You apply here in about two minutes and finish on the hiring platform. The next step is a short AI interview (technical roles include a coding challenge). Passing it is how you qualify for paid tasks, so take it soon after you are invited.

The hiring platform's application for this job asks for your resume, your LinkedIn profile, your phone number, your location and answers to 6 screening questions.

About AI training work

AI training is the human work behind systems that learn from examples and feedback, including testing model responses and reviewing safety behavior. Specialized contributors are paid for applying skills such as security analysis, machine learning, and clear technical communication.

Where you can work

This role is 100% remote, for applicants located in these 48 countries: United Arab Emirates, Argentina, Austria, Bangladesh, Belgium, Bahrain, Canada, Switzerland, Chile, Colombia, Germany, Denmark, Algeria, Egypt, Spain, France, United Kingdom, Ghana, Greece, Indonesia, India, Italy, Jordan, Japan, Kenya, Kuwait, Kazakhstan, Sri Lanka, Morocco, Mexico, Malaysia, Nigeria, Netherlands, Oman, Peru, Philippines, Pakistan, Portugal, Qatar, Saudi Arabia, Singapore, Thailand, Tunisia, Taiwan, United States, Uzbekistan, Vietnam and South Africa.

From OpenTrain AI's job posting, checked 16 Nov 2026.

About OpenTrain AI

A unified board of AI-training jobs with real per-role pay.

How it pays: Stripe payouts to your bank, in the 120 countries its payout docs list.

When it pays: When the employer approves each funded milestone. How often others pay

Interview: on some roles or projects (AI interview (switched on per job by the employer)). How the OpenTrain AI AI interview works

Similar open roles

An experienced engineer?

One profile for every AI training platform. Companies ask us for people with a specific language, country or credential: add yours once, and when a role fits, we introduce you, only with your yes. Free.

Create my profile

Get new OpenTrain AI roles by email

We check the OpenTrain AI job board every hour and email you its newest roles each week, plus similar paid roles elsewhere. Free, unsubscribe anytime.