Cyber Security Engineer

Codefeast is hiring RLE Authors with an offensive security background to build isolated, Dockerized evaluation environments that test how AI coding agents behave during security-sensitive tasks.

Responsibilities:

• Design realistic Dockerized security scenarios based on real offensive-security techniques.
• Create task instructions, repository fixtures, and target environments.
• Write reference solutions in Python.
• Build deterministic verifiers and test harnesses.
• Review AI-agent trajectories to identify failures and unsafe behaviour.
• Revise scenarios based on quality-review feedback.

Requirements:

• Hands-on experience in penetration testing, red teaming, exploit development, or bug bounty work.
• Strong understanding of attack stages such as reconnaissance, Web/API attacks, Privilege escalation, Lateral movement, Active Directory, and cloud misconfigurations; comfortable with Python, Bash, Linux, and Docker.

Skills

AI RED TEAM, AI Safety, AI Security, Adversarial ML, LLM Security, ML Security