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

You hold a Bachelor's or Master’s Degree in Computer Science, Software Engineering, Cybersecurity, Digital Forensics or other related fields.
Proficient in scripting and automation using Python, Bash, or PowerShell.
Experienced with containerization and CI/CD security tools, especially Docker.
Hands-on experience with penetration testing across web, API, network, and infrastructure environments.
Knowledge of vulnerabilities in current AI models, including prompt injections, with knowledge of OWASP Top 10 for Large Language Models (LLMs).
Familiar 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.
You are ready to learn new methods, able to switch between tasks and topics quickly and sometimes work with challenging, complex guidelines.
Our freelance role is fully remote so, you just need a laptop, internet connection, time available and enthusiasm to take on a challenge.

Project details

Recommended projects