AI Jailbreak & Prompt-Injection Security Expert
Posted 6h ago
With Pro, from $2.99 a week: AI tailors your resume to this job, drafts the cover letter and lists the keywords you are missing, in about 30 seconds.
Who can apply
6 countries
Salary
$50–90 / hour
Per hour, USD
Level
Mid level
Contract
Timezone
See description
About the role
IMPORTANT: after you apply, please check your email. We sendyou a link to complete your application — it is not considered until that laststep is done. If you do not see it, check your spam folder.
This is a fully remote position, open to candidates based in 55 countries, including United Kingdom, United States, Canada, Germany, India, France, Netherlands, Singapore.
Pay: $50–$90/hr
Role Title: AI Jailbreak & Prompt-Injection Security Expert
Role Type: Contractor
Location: Remote
We are engaging AI Jailbreak & Prompt-Injection Security Experts to contribute to a cutting-edge customer initiative focused on AI safety and robustness. In this role, you'll apply your expertise to help train next-generation AI systems. Your work will shape how models learn, reason, and perform through high-quality, real-world input. No prior experience in AI is required — your domain knowledge is what matters.
Scope of Work
- Design and implement advanced methodologies for evaluating AI system safety, focusing on ethical jailbreaks, LLM red teaming, prompt injection, and tool-use abuse scenarios.
- Create comprehensive cross-domain elicitation strategies to uncover multi-turn and complex adversarial bypass patterns in AI models.
- Develop, maintain, and update regression test suites that systematically test for jailbreak susceptibility and prompt-injection vulnerabilities.
- Construct robust evaluation frameworks that stress-test AI models against real-world adversarial threats, aiming to enhance overall system robustness.
- Collaborate with technical stakeholders to translate security findings into actionable improvements for model safety and risk mitigation.
- Document methodologies, findings, and best practices in clear, well-structured written reports and presentations for both technical and non-technical audiences.
Preferred Qualifications
- 2+ years of expertise in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security domain
- Proven experience researching, testing, or uncovering vulnerabilities related to ethical jailbreaks, prompt injection, tool-use abuse, or adversarial AI attacks.
- Advanced degree (PhD, MS) in computer science, cybersecurity, machine learning, or a relevant discipline, or equivalent operational/professional background.
- High credibility and recognition within the AI security or adversarial ML community—such as published research, open-source tools, or conference presentations.
- Exceptional written and verbal communication skills, with a strong focus on clear documentation and collaborative problem-solving.
- Prior participation in multi-disciplinary projects or cross-functional AI safety initiatives is a plus.
- Familiarity with current LLM architectures, prompt engineering techniques, and security assessment tools is highly desirable.
How to apply
Apply here with your profile. We will then email you a link to complete yourapplication on the hiring platform — your application is only considered oncethat final step is done.
Originally posted on Himalayas
Interested in this role?
You apply directly with the listing source. Remotavia never charges candidates.
Check your resume
See which keywords from this job your resume is missing.
Track this application
Add it to your board and get a follow-up reminder.
Draft a cover letter
An honest first draft from your resume and this job.
Prepare for interviews
Likely questions based on this job description.
About RemoteJobsOne
Listing details & historyShowHide
- Employer posted
- 20 Nov 2026
- Last confirmed open
- Not yet confirmed
- Source
- Job board
- Degree
- Degree or equivalent experience
- “Advanced degree (PhD, MS) in computer science, cybersecurity, machine learning, or a relevant discipline, or equivalent operational/professional background.”
- Visa
- Not stated
- Timezone
- Not stated
- Languages
- Not stated
- Location evidence
- “This is a fully remote position , open to candidates based in 55 countries, including United Kingdom, United States, Canada, Germany, India, France, Netherlands, Singapore.”
Details are read from the listing text. They are not a guarantee of work authorization; confirm with the employer.
History
- 20 Nov · Added to Remotavia