About OpenTrain
OpenTrain is the centralized, open platform where AI training and data-labeling freelancers find work, consolidate opportunities across platforms, and build a unified AI training portfolio they control. We make specialized AI training work easier to track, apply for, and grow into a durable freelance career.
About this role
OpenTrain is recruiting an AI Jailbreak and Prompt-Injection Security Expert to help evaluate and improve the safety and robustness of AI systems. This contractor role focuses on ethical jailbreaks, LLM red teaming, prompt injection, tool-use abuse, and complex adversarial behavior, combining hands-on security analysis with clear documentation and model-safety recommendations.
What you will do
Design and implement methodologies for evaluating AI system safety across jailbreak, prompt-injection, and tool-use abuse scenarios. Create cross-domain elicitation strategies that reveal multi-turn and complex adversarial bypass patterns. Develop, maintain, and update regression test suites for jailbreak susceptibility and prompt-injection vulnerabilities. Build evaluation frameworks that stress-test models against realistic adversarial threats. Translate security findings into actionable model-safety and risk-mitigation improvements. Document methods, findings, and best practices in structured reports and presentations for technical and non-technical audiences.
Required skills
Bring at least two years of experience in adversarial machine learning, LLM red teaming, AI safety evaluation, or a closely related security domain. Demonstrated experience researching, testing, or uncovering vulnerabilities involving jailbreaks, prompt injection, tool-use abuse, or adversarial AI attacks is required. Strong understanding of current LLM architectures, prompt engineering techniques, and security assessment practices is valuable, along with exceptional written and verbal communication skills and the ability to explain technical findings clearly.
Helpful background
An advanced degree in computer science, cybersecurity, machine learning, or a related discipline is useful, as is equivalent professional or operational experience. Published research, open-source security tools, conference presentations, and participation in multidisciplinary AI safety initiatives are valuable indicators of relevant expertise.
Compensation
The advertised hourly range is $50‑$90 per hour. OpenTrain helps freelancers consolidate AI training opportunities across platforms and build an AI training portfolio around specialized work such as model safety evaluation and adversarial testing.
Why work with OpenTrain
OpenTrain gives freelancers one place to manage AI training opportunities instead of rebuilding proof of work on every platform. A stronger OpenTrain profile helps you show credible experience, discover roles that match your skills, and turn AI training and data-labeling work into a long-term portfolio.
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.