AI Red Team Engineer, LLM Security And Pentesting

About OpenTrain

OpenTrain AI is the hiring and contracting organization for this role and the #1 platform for finding and building careers in AI training and data labeling. OpenTrain helps people start and grow careers teaching AI through flexible, remote projects and a streamlined application process.

• Create a free OpenTrain account and apply in minutes.
• Work remotely on cutting-edge AI projects.
• Build experience in a rapidly growing technology field.

About AI Training And Red Teaming

AI training is the human side of building artificial intelligence. In red-teaming work, specialists deliberately probe AI systems for unsafe, unreliable, or exploitable behavior so models can be evaluated and improved. Your security expertise will help shape how advanced LLMs and AI agents behave.

• Evaluate model behavior using adversarial prompts and structured tests.
• Contribute to safer, more reliable generative AI systems.
• Work remotely with flexible part-time scheduling.

The Role

OpenTrain is hiring multiple AI Red Team Engineers with a strong cybersecurity and penetration testing background, hands-on LLM security expertise, and advanced C1 English communication skills. This is an intermediate-level, part-time contractor role requiring less than 20 hours per week and paying $40 USD per hour.

You will follow detailed project guidelines, collaborate remotely, and uphold strict ethical and safety standards while evaluating LLMs, agents, and retrieval-augmented generation pipelines.

• Employment type: Part-time contractor
• Time requirement: Less than 20 hours per week
• Pay: $40 USD per hour
• Work arrangement: Remote
• OpenTrain is hiring multiple contributors

What You’ll Do

You will design and execute adversarial evaluations across LLMs, AI agents, and RAG pipelines. The work combines security testing, scripting, evaluation design, technical writing, and careful grading of model behavior.

• Craft and automate attack prompts, including prompt injection and jailbreak attempts.
• Build repeatable test suites for LLM, agent, and RAG evaluations.
• Probe function-calling and tool-use behavior.
• Define scoring rubrics and grade model responses and behaviors.
• Document reproducible findings with clear risk ratings.
• Propose mitigations for identified vulnerabilities.
• Contribute small scripts and utilities to scale red-team testing.
• Communicate findings clearly and follow ethical and safety requirements.

Requirements And Technical Qualifications

Applicants should have a Bachelor’s or Master’s degree in Computer Science, Software Engineering, Cybersecurity, Digital Forensics, or a related field, along with practical security experience. The role requires the ability to communicate clearly in advanced C1 English.

• Hands-on penetration testing across web, API, network, and infrastructure environments.
• Familiarity with cloud security, container security, and secure SDLC practices.
• Strong scripting and automation skills with Python, Bash, or PowerShell.
• Experience with containerization and CI/CD security tools such as Docker.
• Knowledge of LLM vulnerabilities, including prompt injection, jailbreaks, and data leakage.
• Knowledge of the OWASP Top 10 for LLMs.
• Familiarity with AI red-teaming and evaluation frameworks such as garak or PyRIT.
• Experience evaluating LLMs, agents, and RAG pipelines.
• Offensive exploitation and reverse engineering experience, such as Ghidra or an equivalent tool.
• Knowledge of OS security, including Linux privilege escalation and Windows internals.
• Ability to write clear rubrics, adversarial prompts, and concise technical reports.
• Secure coding practices suitable for full-stack review.
• Availability to complete a HackerRank and platform assessment immediately after screening.

Preferred Experience

The strongest candidates combine practical offensive security skills with a clear understanding of modern AI attack surfaces. Experience contributing to LLM security work or working at a leading AI or security organization is a plus, but it is not listed as a required qualification.

• Prior experience at a leading AI or security organization.
• Previous work shipping LLM security projects.
• Experience turning complex security findings into actionable, concise recommendations.

Eligibility And Restricted Locations

This project is worldwide in scope, but applicants in the following locations are ineligible: Iran, Cuba, North Korea, Syria, Sudan, Venezuela, Myanmar, Switzerland, China, Taiwan, Kenya, Armenia, Israel, Kazakhstan, UAE, Netherlands, Serbia, Kyrgyzstan, Turkey, Uzbekistan, Belarus, Russia, Ukraine, Abkhazia, and South Ossetia.

The following United States states are also restricted: Alaska, Arkansas, California, Connecticut, Delaware, Georgia, Hawaii, Illinois, Indiana, Kansas, Louisiana, Maine, Maryland, Massachusetts, Nebraska, Nevada, New Hampshire, New Jersey, New Mexico, Ohio, Oregon, Tennessee, Utah, Vermont, Washington, West Virginia.

Restricted territories and regions include Antarctica, Aruba, Åland Islands, Saint Barthélemy, Bonaire, Sint Eustatius and Saba, Bouvet Island, Cocos (Keeling) Islands, Democratic Republic of the Congo, Cook Islands, Christmas Island, Western Sahara, Falkland Islands (Malvinas), French Guiana, Guadeloupe, South Georgia and the South Sandwich Islands, Heard Island and McDonald Islands, British Indian Ocean Territory, Northern Mariana Islands, Martinique, New Caledonia, Norfolk Island, Niue, French Polynesia, Saint Pierre and Miquelon, Pitcairn, Réunion, Saint Helena, Ascension and Tristan da Cunha, Svalbard and Jan Mayen, Sint Maarten (Dutch part), French Southern Territories, Tokelau, United States Minor Outlying Islands, Holy See, Virgin Islands (British), Wallis and Futuna, and Mayotte.

How To Apply

Create a free OpenTrain account to begin your application. After screening, you must be available to complete both the HackerRank assessment and the platform test immediately. If selected, you will work as a remote, part-time contractor supporting structured AI security evaluations.

• Review the technical requirements and location restrictions.
• Apply through OpenTrain.
• Complete the required assessments promptly after screening.
• Begin flexible, paid work helping evaluate advanced AI systems.