AI Red Team Engineer for LLMs (Security Certification)

The Work

You will evaluate and red team large language models and AI agents for safety issues and security vulnerabilities. You will create repeatable, automated test cases and build the scripts, tools, environments, and test harnesses needed to assess model behavior.

The work may also include security research, realistic attack scenarios, advice on secure coding and platform hardening, and clear reports with steps to reproduce each finding.

• Test AI models and agents for vulnerabilities, including prompt injection and other LLM security risks.
• Create offline, reproducible, and automatically evaluated test cases.
• Build automation scripts, custom tools, testing environments, and test harnesses.
• Use or work with tools and frameworks such as garak or PyRIT.
• Document security findings with clear reproduction steps.

What It Pays And Takes

This is part-time, remote contract work with flexible hours. The role is open worldwide, subject to the project's eligible-location requirements.

• Pay: $40 per hour.
• Time: Less than 20 hours per week.
• Work setup: Remote, part time, with flexible hours.
• Language: Advanced English proficiency at C1 level or higher.
• Education: A bachelor's or master's degree in computer science, software engineering, cybersecurity, digital forensics, or a related field.
• Certification: At least one recognized cybersecurity or red team certification, with a public Credential.net link for verification.
• Technical skills: Strong scripting in Python, Bash, or PowerShell.
• Security experience: Docker, CI/CD security tooling, and penetration testing across web, API, network, and infrastructure systems.
• AI security knowledge: LLM risks, including prompt injection, and the OWASP Top 10 for LLMs.
• Application materials: A resume in English and a public certification credential link.

How It Works

Apply on OpenTrain. The employer reviews applications there.

About AI Training Work

AI training is the human work behind artificial intelligence, including testing model responses, finding safety problems, and preparing examples that help systems behave better. OpenTrain helps people find and build careers in this field, where cybersecurity specialists are needed to test advanced models and reduce real-world risks.

Where you can work

This role is 100% remote: you can work from any country except Andorra, Afghanistan, Barbados, Burkina Faso, Burundi, Brazil, Belarus, Belize, DR Congo, Central African Republic, Congo (Republic), Cameroon, China, Cuba, Cape Verde, Djibouti, Dominica, Eritrea, Fiji, Micronesia, Grenada, Georgia, Guinea, Equatorial Guinea, Guinea-Bissau, Honduras, Haiti, Iraq, Iran, Kyrgyzstan, Kiribati, Comoros, St. Kitts and Nevis, North Korea, Lebanon, Liberia, Lesotho, Libya, Montenegro, Marshall Islands, Mali, Myanmar, Mauritania, Maldives, Malawi, Nicaragua, Nepal, Nauru, Papua New Guinea, Palestine, Palau, Russia, Solomon Islands, Seychelles, Sudan, Sierra Leone, Somalia, Suriname, South Sudan, São Tomé and Príncipe, Syria, Eswatini, Chad, Togo, Tajikistan, Timor-Leste, Turkmenistan, Tonga, Tuvalu, Ukraine, Uganda, Vatican City, St. Vincent and Grenadines, Venezuela, Vanuatu, Samoa, Yemen, Zambia and Zimbabwe.