AI Red Team Engineer — LLM Security & Pentesting (C1 English)

About OpenTrain

OpenTrain is a central job board for data-labeling and AI-training work. We aggregate roles from many AI companies and labeling platforms so people can discover remote, flexible projects in one place.

Creating an OpenTrain account is free, and applying takes only a few minutes. We connect qualified contributors with meaningful work that helps shape how AI systems behave.

About AI Training & Red Teaming

AI training—also called data labeling, annotation, or human feedback work—covers tasks where people prepare, test, and review examples that modern models learn from. Red teaming and adversarial evaluation focus on finding and mitigating model weaknesses so systems are safer and more reliable.

This role sits at the intersection of cybersecurity and model evaluation: you will probe LLM attack surfaces, craft adversarial prompts, and help build repeatable test suites that measure real-world risks.

The Role

We are hiring multiple AI Red Team Engineers to design and execute adversarial evaluations of LLMs, agents, and RAG pipelines in a remote, part-time contract capacity. Work is less than 20 hours per week and paid at $40 USD per hour.

You will follow detailed guidelines and strict ethical and safety standards while collaborating with other engineers and evaluators to produce reproducible findings and actionable mitigations.

• Commitment: Less than 20 hours/week
• Pay: $40 USD per hour (PAY_PER_HOUR)
• Employment type: Contractor, Part-time
• Labeling type: RED_TEAMING (TEXT); labeling software: OTHER
• Experience level: Intermediate

What You’ll Do

Design, run, and automate adversarial attacks against LLMs, agents, and retrieval-augmented generation (RAG) pipelines. Create test suites that stress prompt injection, jailbreaks, data exfiltration, function-calling and tool use.

Document findings with reproducible steps, risk ratings, concise reports, and suggested mitigations. Build small scripts and utilities to scale testing and integrate with CI/CD where appropriate.

• Craft and automate attack prompts and payloads for LLMs and agents
• Build test suites and scoring rubrics; grade model behaviors consistently
• Probe function-calling/tool use and RAG retrieval paths for leakage
• Produce reproducible documentation with risk ratings and mitigation suggestions
• Contribute scripts/utilities to scale and automate red-team workflows

Requirements & Qualifications

You must have a Bachelor’s or Master’s in Computer Science, Software Engineering, Cybersecurity, Digital Forensics, or a related field, and hands-on penetration testing experience across web, API, network, and infrastructure.

This project requires strong scripting and automation skills and domain knowledge specific to LLM security and offensive techniques.

• Degree: Bachelor’s or Master’s in a relevant technical field
• Pentesting: Practical experience with web, API, network, and infrastructure testing
• Scripting: Proficiency in Python plus Bash or PowerShell for automation
• Containers/CI: Experience with containerization and CI/CD security (e.g., Docker) and secure SDLC practices
• LLM security: Familiarity with prompt injection, jailbreaks, data leakage, and the OWASP Top 10 for LLMs
• Frameworks: Experience with red-teaming/eval frameworks such as garak or PyRIT
• Reverse engineering & OS security: Offensive exploitation and reverse engineering (e.g., Ghidra) and OS-level experience (Linux privilege escalation, Windows internals)
• Communication: Ability to write clear rubrics, adversarial prompts, and concise reports in advanced (C1) English
• Assessment: Availability to complete a HackerRank + platform assessment immediately after screening

Who Should Apply / Nice-To-Haves

This role is aimed at security professionals with hands-on pentesting and automation skills who want to focus on LLM and agent security. If you enjoy building reproducible tests and writing clear, concise findings, you’ll fit well here.

Preferred but not strictly required: prior experience at leading AI or security organizations or shipping LLM security work; these are listed as pluses.

• Ideal background: cybersecurity engineers, red teamers, security researchers with scripting skills
• Plus: prior LLM security or AI-security product experience at notable organizations

How It Works & Eligibility

Screening includes a HackerRank test plus a platform assessment; you must be available to complete these immediately after initial screening. Work is remote and contract-based with flexible hours under 20 hours/week.

Candidates must follow ethical testing rules and project-specific guidelines; you will not perform unauthorized testing or violate safety protocols.

• Start process: screening → HackerRank + platform assessment → contract onboarding
• Work model: remote, part-time contractor; follow provided testing guidelines and safety rules

Restricted Locations

The following locations are ineligible for this role: 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, South Ossetia; United States (restricted states): 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; and the following territories/regions: 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, Mayotte.