AI Red Team Engineer for LLM Security

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. Create a free profile, discover cutting-edge projects, and apply in minutes.

AI training is the human side of building artificial intelligence. Specialists help models become safer and more useful by testing behavior, reviewing outputs, creating high-quality evaluation data, and identifying vulnerabilities.

About AI Security Training

Red teaming AI models and agents helps uncover prompt injection, unsafe behavior, security weaknesses, and other risks before systems are deployed. This work combines cybersecurity expertise with structured evaluation, automation, and clear technical reporting.

The role is fully remote and part time, with flexible hours and a workload of less than 20 hours per week. Your work can directly influence how advanced AI systems are tested, hardened, and operated.

The Role

OpenTrain AI is seeking an AI Red Team Engineer to evaluate and red team large language models, AI agents, and RAG pipelines for safety and vulnerabilities. You will create offline, reproducible, and auto-evaluable test cases while developing the automation and environments needed to run realistic security assessments.

The position is intended for intermediate-level practitioners with strong offensive security, scripting, and application security experience. Compensation varies by location and experience, with the role description specifying rates up to $55 USD per hour; the listing includes a $40 USD hourly rate.

• Employment type: Part-time contractor
• Schedule: Flexible, less than 20 hours per week
• Work arrangement: Remote
• Language: Advanced English proficiency at C1 level or higher
• Location: Worldwide in eligible locations

What You'll Do

You will investigate AI security risks through hands-on testing, offensive research, and repeatable evaluation. Findings should be documented clearly enough for others to reproduce, validate, and address them.

• Evaluate LLMs, AI agents, and RAG pipelines for safety issues and vulnerabilities.
• Create offline, reproducible, and auto-evaluable security test cases.
• Build automation scripts, custom tools, test environments, and test harnesses.
• Design realistic attack scenarios involving prompt injection and other LLM risks.
• Conduct penetration testing across web, API, network, and infrastructure environments.
• Contribute to security research and document findings with clear reproduction steps.
• Advise on secure coding, platform hardening, and application security improvements.
• Use offensive exploitation and reverse engineering skills where appropriate.

Required Qualifications

Applicants must submit a resume in English, reside in an eligible location, and provide public evidence of at least one recognized cybersecurity or red team certification through a credential.net link for verification. A reliable laptop and internet connection are required.

• Bachelor’s or Master’s degree in computer science, software engineering, cybersecurity, digital forensics, or a related field.
• At least one recognized security or red team certification with a public credential.net verification link.
• Strong scripting and automation skills in Python, Bash, or PowerShell.
• Experience with Docker and CI/CD security tooling.
• Hands-on penetration testing across web, API, network, and infrastructure environments.
• Solid network and application security fundamentals.
• Knowledge of LLM vulnerabilities, including prompt injection and the OWASP Top 10 for LLMs.
• Ability to learn quickly, follow complex guidelines, and context switch across tasks.

Preferred Security Experience

The role values practical evidence of offensive security and AI security work. Familiarity with specialized LLM assessment frameworks and operating-system security techniques is especially useful.

• Preferred certifications include OSCP, OSWE, OSEP, OSED, OSEE, OSWP, CRTP, CRTE, CRTO, CRTL, RTO, CARTP, GPEN, GWAPT, GXPN, GREM, GCTI, GCIH, or GNFA.
• For junior candidates, valid foundational certifications include CEH, PenTest+, CySA+, ECSA, AWS Security Specialty, Azure Security Engineer Associate, Google Cloud Professional Cloud Security Engineer, or CCSP.
• Familiarity with garak or PyRIT.
• Experience evaluating security for LLMs, AI agents, and RAG pipelines.
• Understanding of Linux privilege escalation, Windows internals, and secure coding practices for full-stack development.
• Experience with reverse engineering tools such as Ghidra.
• Public bug bounty write-ups, CVEs, or competition results.

Who Should Apply

This opportunity is suited to cybersecurity engineers, penetration testers, red teamers, application security specialists, and security researchers who want to help shape the safety of advanced AI systems. Advanced English communication is required for following detailed guidance and producing precise technical documentation.

• You have a verifiable cybersecurity or red team certification.
• You can automate repeatable security tests with Python, Bash, or PowerShell.
• You understand both conventional application security and emerging LLM attack methods.
• You are comfortable working independently in a flexible, part-time remote setting.

Location Eligibility

Applicants must begin the interview by confirming their location. The role is not available in the following restricted locations: Iran, Cuba, North Korea, Syria, Sudan, Venezuela, Myanmar, Switzerland, China, Taiwan, Kenya, Armenia, Israel, Kazakhstan, United Arab Emirates, Netherlands, Serbia, Kyrgyzstan, Turkey, Uzbekistan, Belarus, Russia, Ukraine, Abkhazia, South Ossetia, 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, 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, French Southern Territories, Tokelau, United States Minor Outlying Islands, Holy See, British Virgin Islands, Wallis and Futuna, and Mayotte.

Apply Through OpenTrain

Create a free OpenTrain account and submit your English resume and application. Be prepared to share your location at the start of the interview and provide the public credential.net link for your required certification.

• Confirm that you live in an eligible location.
• Prepare your English-language resume.
• Include your public certification verification link.
• Highlight relevant red teaming, penetration testing, scripting, LLM security, or research experience.