AI Red Team Engineer - Portuguese

Responsibilities

• Craft prompts and scenarios to test model guardrails
• Explore creative ways to bypass restrictions
• Systematically document outcomes
• Collaborate with engineers and safety researchers to share findings and improve system defenses

Requirements

• Bachelor's or Master’s Degree in Computer Science, Software Engineering, Cybersecurity, etc.
• Advanced English (C1) or above
• Adversarial thinking
• Knowledge of vulnerabilities in AI models
• Experience in AI/ML security, evaluation, and red teaming
• Proficient in Python, Bash, or PowerShell
• Familiar with AI red-teaming frameworks like garak or PyRIT

Preferred Qualifications

• Physical-world adversarial testing
• Experience with Docker and CI/CD security
• Offensive exploitation and exploit development
• Reverse engineering with tools like Ghidra
• Network and application security expertise
• OS security concepts (Linux privilege escalation, Windows internals)
• Secure coding practices for full-stack development

Benefits

• Rates up to $55/hour based on skills and experience
• Part-time, remote freelance opportunity
• Work on advanced AI projects
• Influence future AI model development

About the Company

LILT's mission is to make the world's information available to everyone, regardless of language. We provide multilingual AI and human-verified services to enterprises, governments, and AI developers globally.