AI Red Team Engineer - Simplified Chinese (Remote)

About the Role

We are looking for an AI Red Team Engineer - Remote to join our team at LILT. This role focuses on adversarial testing of AI systems, including large language models (LLMs) and multimodal models. As an AI Red Team Engineer, you will collaborate with engineers and safety researchers to ensure the robustness and security of AI systems.

What You'll Do

• Collaborate on adversarial testing of AI systems, crafting prompts and scenarios to test model guardrails.
• Explore innovative ways to bypass restrictions and document outcomes systematically.
• Utilize your deep understanding of generative AI models to identify vulnerabilities.
• Apply strong analytical skills for data analysis and natural language processing (NLP).
• Commit to ethical hacking practices while conducting tests.
• Work flexibly as a freelancer, contributing to advanced AI projects.
• Enhance your portfolio with valuable experience in AI/ML security and red teaming.
• Influence the development of future AI models in your field.

Requirements

• Bachelor's or Master’s Degree in relevant fields.
• Advanced English proficiency (C1 or above) is required.
• Experience in AI/ML security and red teaming.
• Proficient in scripting using Python, Bash, or PowerShell.
• Knowledge of vulnerabilities in AI models and adversarial thinking skills.
• Ability to work with complex guidelines and frameworks.

Nice to Have

• Familiarity with red-teaming frameworks.
• Experience in cybersecurity principles.

What We Offer

• Competitive pay rates up to $55/hour.
• Part-time, remote freelance work with flexible hours.
• Opportunity to work on advanced AI projects.
• Enhance your portfolio with valuable experience.
• Influence future AI models in your field.