AI Red Team Engineer - Italian
AI Red Team Engineer - Italian
AI Red Team Engineer - Italian
Lilt
LILT is a leading company in AI-driven translation services, seeking freelance AI Red Team experts to conduct adversarial testing on AI systems. The role involves crafting prompts to test model guardrails and collaborating with engineers to enhance system defenses. Candidates should have a deep understanding of generative AI, cybersecurity principles, and data analysis, along with a commitment to ethical hacking.
Qualification
- Deep understanding of generative AI and main models
- Experience in cybersecurity principles, including threat modeling and penetration testing
- Strong analytical skills for data analysis and NLP
- Commitment to ethical hacking and responsible disclosure
- Bachelor's or Master’s Degree in Computer Science, Software Engineering, Cybersecurity, or related fields
Responsibility
- Collaborate on projects focused on adversarial testing of AI systems
- Craft prompts and scenarios to test model guardrails
- Explore creative ways to bypass restrictions
- Systematically document outcomes of testing
- Collaborate with engineers and safety researchers to share findings and improve system defenses
