AI Red Team Engineer for LLMs (Security Certification Required)

Candidates should have an advanced command of English (C1 or higher), a Bachelor’s or Master’s in CS, Software Engineering, Cybersecurity, Digital Forensics or related, and at least one recognized cybersecurity or red team certification with a public credential.net link for verification. Strong scripting skills in Python, Bash or PowerShell are required, plus experience with Docker and CI/CD security tooling, penetration testing across web, API, network and infrastructure, and familiarity with LLM risks including prompt injection and the OWASP Top 10 for LLMs. Experience with frameworks such as garak or PyRIT is valuable. Applicants must submit a resume in English and reside in an eligible location.

You will evaluate and red team AI models and agents for safety and vulnerabilities, create offline reproducible and auto-evaluable test cases, and build automation scripts, custom tools, environments and test harnesses. Work may include contributing to security research, designing realistic attack scenarios, advising on secure coding and platform hardening, and documenting findings with clear reproduction steps. This is part-time, remote work with flexible hours.