Unleash Your Inner Hacker: AI Red Team Experts Wanted
LILT is revolutionizing global communication through AI, and we need your help to secure the future. We're not just translating words; we're making information accessible to everyone, regardless of language. Join us in pushing the boundaries of AI and ensuring its safe and responsible deployment.
We're seeking talented and driven freelance AI Red Team experts to join our mission. If you're passionate about breaking things to make them better, possess a deep understanding of AI vulnerabilities, and thrive in a fast-paced environment, we want to hear from you.
Your Mission, Should You Choose To Accept It: As an AI Red Team expert, you'll be at the forefront of adversarial testing, focusing on: LLMs & Multimodal Models: Identifying weaknesses and vulnerabilities in large language models and multimodal systems. Your daily adventures will involve crafting ingenious prompts and scenarios to expose vulnerabilities, creatively bypassing restrictions, and meticulously documenting your findings. You'll be thinking like a real-world adversary, uncovering weaknesses and collaborating with our engineers and safety researchers to fortify our AI defenses. Are You the Right Agent? We're looking for individuals with a strong foundation in the following areas: Generative AI Mastery: Deep understanding of generative AI models, including architectures, training processes (prompt engineering, fine-tuning, RLHF), and potential failure modes. Core
Inference Services: Attacking and securing inference services to prevent malicious use.
RAG/Embeddings: Finding loopholes and exploits within Retrieval-Augmented Generation (RAG) systems and embeddings.
Product Integrations: Ensuring the security and integrity of AI integrations within our products.
Cybersecurity Expertise: Solid grasp of cybersecurity principles, threat modeling, vulnerability assessment, and penetration testing. You should be able to identify attack vectors and simulate real-world threats.
Data Analysis & NLP Skills: Strong analytical skills to dissect model outputs, identify biases/errors, and recognize response patterns. NLP background is a significant plus.
Ethical Hacking Ethos: Unwavering commitment to ethical hacking principles and responsible disclosure.