AI Red Team Engineer — LLM Security

About OpenTrain

OpenTrain is the #1 platform for building careers in AI training and data labeling. We connect skilled contributors with real projects that shape how state-of-the-art AI systems behave. Creating an OpenTrain account is free and is where people start and grow careers teaching AI.

About AI training and red teaming

AI training (data labeling and human-feedback work) is the human side of building AI. Red teaming LLMs is a specialist area within this field: security experts design, execute, and document realistic attacks to reveal model and system weaknesses so engineers can fix them.

This work is often 100% remote, flexible, and accessible to people who have the required security expertise. Contributors directly influence AI safety and platform hardening by producing reproducible test cases, tooling and clear remediation guidance.

Role overview

We are hiring part-time AI Red Team Engineers to evaluate LLMs, agents, and RAG pipelines for safety and vulnerabilities. You will design and execute offensive test cases, build automation and test harnesses, and document reproducible findings for engineering teams.

This is contract, remote work (less than 20 hours/week) with flexible scheduling. You must submit an English resume and public verification of at least one recognized cybersecurity or red-team certification.

What you'll do

You will simulate realistic attacker behavior against models and supporting infrastructure, produce offline reproducible tests, and create auto-evaluable cases that scale across environments.

You will build and maintain automation scripts, custom tools, containerized test environments, and CI/CD security tooling to run continuous red-team checks and regression tests.

• Design and execute red-team scenarios targeting LLMs, agents, and RAG pipelines.
• Create reproducible, documented test cases with clear reproduction steps and remediation suggestions.
• Develop scripts, Docker-based environments, and test harnesses to automate evaluation and scoring.
• Advise on secure coding, platform hardening, and integration of security checks into CI/CD pipelines.
• Contribute to security research, writeups, and actionable reports suitable for engineering teams.

Minimum requirements

You must meet all items in this list and be able to provide the requested public verification links and documents.

Applicants should be ready to confirm eligibility and location early in the interview process — candidates residing in restricted countries or regions listed below are not eligible.

• Advanced command of English (C1 or higher).
• Bachelor’s or Master’s 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 link for verification.
• Strong scripting and automation skills in Python, Bash, or PowerShell.
• Hands-on penetration testing experience across web, API, network, and infrastructure.
• Experience with Docker and CI/CD security tooling.
• Practical knowledge of LLM-specific risks (prompt injection, OWASP Top 10 for LLMs) and familiarity with tools like garak or PyRIT.
• Reliable laptop and internet connection; ability to follow complex guidelines and switch context across tasks.
• Resume in English required.

Preferred qualifications

We value deep offensive skills, security research output, and broad systems knowledge. Preference will be given to candidates with documented public work and advanced certifications.

• Recognized certifications: OffSec (OSCP, OSWE, OSEP, OSED, OSEE, OSWP); red-team certs (CRTP, CRTE, CRTO, CRTL, RTO, CARTP); SANS/GIAC (GPEN, GWAPT, GXPN, GREM, GCTI, GCIH, GNFA).
• Foundational certs acceptable for junior candidates: CEH, PenTest+, CySA+, ECSA, cloud security certs (AWS/Azure/GCP security specialties).
• Public evidence of bug bounty writeups, CVEs, or competition results.
• Experience with offensive exploitation, reverse engineering (Ghidra), Windows internals, Linux privilege escalation, and secure full-stack development practices.

Location, hours, and compensation

This role is remote and part-time (typically less than 20 hours/week) with flexible scheduling. You must reside outside the restricted list below and will be asked to confirm your location early in the process.

Compensation varies by location and experience. Typical starting pay is $40 USD/hour; total compensation may vary by experience and location (up to $55 USD/hour in some cases).

• Eligible worldwide except restricted countries and regions listed in the job description; applicants must confirm their location.
• Contractor, part-time engagement with flexible hours; provide availability when applying.

How to apply and next steps

To apply, submit a resume in English and a public credential.net link for your required security or red-team certification. Include brief notes on relevant hands-on projects, public writeups, or CVEs if available.

We will verify credentials and confirm location eligibility early in the process. Selected candidates will complete technical screening and sample red-team tasks to demonstrate scripting, tooling, and attack design abilities.

• Required with application: English resume + public credential.net verification link for a qualifying certification.
• Optional but helpful: links to public writeups, GitHub repos, CVEs, or bug bounty reports.

Restricted locations (ineligible)

Candidates residing in the following countries, territories, or regions are not eligible to apply: 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; United States 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; 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.