Mindrift is looking for a Freelance AI Red Team Engineer to evaluate and improve the safety and capabilities of Generative AI models and systems. You will work on projects from major tech innovators, focusing on security research and building robust testing frameworks.

What You'll Do

Evaluate and red team AI models, agents, and machine learning systems for vulnerabilities and safety risks.
Create offline reproducible and auto-evaluable test cases to assess AI agent safety and capability.
Develop and implement automation scripts, custom tools, environments, and test harnesses.
Lead or contribute to security research initiatives in AI safety, creating realistic and challenging attack scenarios.
Advise on cybersecurity best practices and policy implications.

What We're Looking For

A Bachelor's or Master’s Degree in Computer Science, Software Engineering, Cybersecurity, Digital Forensics, or a related field.
Advanced (C1) or above level of English proficiency.
Proficient in scripting and automation using Python, Bash, or PowerShell.
Experienced with containerization and CI/CD security tools, especially Docker.
Hands-on penetration testing experience across web, API, network, and infrastructure environments.
Knowledge of vulnerabilities in current AI models, including prompt injections, and the OWASP Top 10 for Large Language Models (LLMs).
Familiarity with AI red-teaming frameworks such as garak or PyRIT.
Experience in AI/ML security, evaluation, and red teaming, particularly with LLMs, AI agents, and RAG pipelines.
Proficient in offensive exploitation and exploit development.
Skilled in reverse engineering using tools like Ghidra or equivalents.
Expertise in network and application security, including web application security.
Knowledge of operating system security concepts such as Linux privilege escalation and Windows internals.
Familiar with secure coding practices for full-stack development.
Readiness to learn new methods, switch between tasks quickly, and sometimes work with challenging, complex guidelines.
Ability to work fully remote, requiring a laptop, a reliable internet connection, available time, and enthusiasm.

Technical Stack

Python, Bash, PowerShell, Docker, Ghidra

Benefits & Compensation

Get paid for your expertise, with rates that can go up to $15/hour depending on your skills, experience, and project needs.
Take part in a part-time, remote, freelance project that fits around your primary professional or academic commitments.
Work on advanced AI projects and gain valuable experience that enhances your portfolio.
Influence how future AI models understand and communicate in your field of expertise.