AI Red Team Engineer — LLM Security (Cert Required)

About OpenTrain

OpenTrain is the #1 platform for finding and building careers in AI training and data labeling. We connect people to cutting-edge projects where human expertise directly shapes how modern AI systems behave.

Working through OpenTrain gives you access to flexible, remote AI-training work across the industry—ideal for skilled technical contributors who want part-time contracts and practical impact on model safety and behavior.

About AI training and red teaming

AI training (also called data labeling or human feedback work) is the human side of building artificial intelligence. In security-focused roles you test, probe, and improve model behavior so systems are safer and more robust.

Red teaming for LLMs blends offensive security skills with prompt- and model-level understanding: you create realistic attack scenarios, evaluate model responses, and build reproducible tests that help engineers mitigate risks.

The role

We’re hiring an AI Red Team Engineer to evaluate LLMs, agents, and retrieval-augmented systems for safety and vulnerabilities. This part-time, remote contractor role (<20 hours/week) combines hands-on penetration testing, security research, and automation.

You will design reproducible, auto-evaluable test cases and build tooling, test harnesses, and scripts to scale red-team coverage and integrate tests into CI/CD pipelines.

What you'll do

• Perform offensive evaluations of AI models, agents and RAG pipelines focusing on prompt injection, model manipulation, data exfiltration, and other LLM-specific risks.
• Create offline, reproducible test cases with clear reproduction steps and automated checks so results can be evaluated programmatically.
• Build automation scripts, custom tools, containerized environments, and CI/CD integrations to run red-team suites at scale.
• Design realistic attack scenarios, advise on secure coding and platform hardening, and document findings for engineering teams and stakeholders.
• Contribute to security research and optionally prepare reproducible artifacts such as PoCs, bug reports, or write-ups when applicable.

Minimum qualifications

• Advanced command of English (C1 or higher). Resume must be submitted in English.
• 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 (required).
• Strong scripting and automation skills in Python, Bash or PowerShell.
• Experience with Docker and CI/CD security tooling and workflows.
• Hands-on penetration testing across web, API, network and infrastructure; solid network and application security fundamentals.
• Familiarity with LLM vulnerabilities (including prompt injection) and the OWASP Top 10 for LLMs.
• Reliable laptop and internet connection; ability to learn quickly and follow complex guidelines.

Preferred skills and credentials

• Experience evaluating security for LLMs, AI agents and RAG pipelines; offensive exploitation and reverse-engineering skills (tools like Ghidra) are valued.
• Familiarity with frameworks such as garak or PyRIT is useful.
• Preferred certifications: OffSec (OSCP, OSWE, OSEP, OSED, OSEE, OSWP), specialized red team certs (CRTP, CRTE, CRTO, CRTL, RTO, CARTP), or SANS/GIAC (GPEN, GWAPT, GXPN, GREM, GCTI, GCIH, GNFA).
• Foundational certs (CEH, PenTest+, CySA+, ECSA) or cloud security certs (AWS Security Specialty, Azure Security Engineer Associate, Google Cloud Professional Cloud Security Engineer, CCSP) are acceptable for junior candidates.
• Public evidence of bug bounty write-ups, CVEs, or competition results is a plus.

Location, eligibility and compensation

This is fully remote and worldwide in scope, but applicants must reside in an eligible country. During the first interview we will ask for your current country to confirm eligibility—do not proceed if you are located in a restricted jurisdiction.

Compensation varies by location and experience. Typical pay starts at $40 USD per hour with opportunities up to $55 USD per hour depending on experience and location. This is a contractor, part-time role (<20 hours/week).

• Candidates located in the following restricted countries or territories are not eligible to apply: Iran, Cuba, North Korea, Syria, Sudan, Venezuela, Myanmar; Switzerland; China, Taiwan; Kenya; Armenia, Israel, Kazakhstan, UAE, Netherlands, Serbia, Kyrgyzstan, Turkey, Uzbekistan, Belarus, Russia, Ukr

How to apply

To apply, submit your resume in English and include a public credential.net link for at least one recognized security or red-team certification. In your application please state your current country of residence (we will verify eligibility at interview start).

Also include a short note (2–4 sentences) summarizing relevant red team or LLM security experience and the tools/frameworks you’ve used (for example: Docker, CI/CD security tooling, garak, PyRIT, Ghidra). We will follow up with qualified candidates to schedule a technical interview.