Job Title
AI Jailbreak & Prompt-Injection Security Expert – AI Trainer
Job Type
Contractor
Compensation Structure
Hourly contract position. Compensation is paid based on hours worked and approved project time.
Location
Remote
Job Summary
We are looking for AI Jailbreak & Prompt-Injection Security Experts to support AI training and evaluation by contributing advanced expertise in AI safety, adversarial machine learning, LLM security, and red teaming. In this role, you will help improve next-generation AI systems by applying your knowledge of prompt injection, jailbreak techniques, adversarial testing, and AI robustness evaluation.
This is an hourly-paid contract opportunity, not a traditional AI engineering or security operations role. Contributors will complete project-based AI training and evaluation tasks that help AI models better understand adversarial behavior, model safety, prompt security, and responsible AI deployment.
No prior AI training experience is required. What matters most is your expertise in AI security, adversarial testing, and your ability to communicate complex technical concepts clearly.
Key Responsibilities
- Contribute to AI training, benchmarking, and evaluation projects focused on AI safety and adversarial robustness.
- Design and implement evaluation methodologies for ethical jailbreaks, prompt injection, LLM red teaming, and tool-use abuse scenarios.
- Develop comprehensive elicitation strategies to identify multi-turn attacks, prompt manipulation, and adversarial bypass techniques.
- Build and maintain regression test suites that evaluate AI models for jailbreak susceptibility and prompt-injection vulnerabilities.
- Develop evaluation frameworks that simulate real-world adversarial threats to improve AI robustness and safety.
- Review AI-generated outputs, security evaluations, and benchmarks for accuracy, consistency, and security effectiveness.
- Document methodologies, findings, best practices, and technical recommendations for both technical and non-technical stakeholders.
- Collaborate with multidisciplinary teams to improve AI safety frameworks and model security through continuous evaluation and feedback.
Required Skills and Qualifications
- 2+ years of professional experience in adversarial machine learning, AI safety, LLM red teaming, cybersecurity, or a closely related field.
- Strong understanding of prompt injection, jailbreak techniques, adversarial AI attacks, and AI safety evaluation methodologies.
- Experience researching, testing, or evaluating vulnerabilities involving large language models, tool-use abuse, or prompt engineering.
- Strong analytical and technical problem-solving skills with exceptional attention to detail.
- Excellent written and verbal communication skills with the ability to clearly explain complex AI security concepts.
- Ability to work independently in a remote, collaborative environment.
Preferred Qualifications
- Advanced degree (MS or PhD) in Computer Science, Cybersecurity, Machine Learning, Artificial Intelligence, or a related discipline, or equivalent professional experience.
- Published research, open-source contributions, conference presentations, or recognized work within the AI security or adversarial machine learning community.
- Experience participating in multidisciplinary AI safety, security, or model evaluation initiatives.
- Familiarity with modern LLM architectures, prompt engineering techniques, AI evaluation methodologies, and security assessment tools.
- Interest in advancing responsible AI through rigorous safety testing and adversarial evaluation.
Additional Information
This opportunity is ideal for AI security and adversarial machine learning professionals who want to help shape the next generation of safe and reliable AI systems. Your contributions will directly improve how advanced AI models detect, resist, and reason about prompt injection, jailbreak attempts, adversarial behavior, and emerging AI security threats while helping establish robust evaluation standards for responsible AI deployment.
Job Type: Contract
Pay: $50.00 - $90.00 per hour
Benefits:
Work Location: Remote
