AI Red Team: Break Our AI (and Help Us Build It Better)
LILT is on a mission to make the world's information accessible to everyone, regardless of language. We're using cutting-edge AI and human expertise to revolutionize translation. Join us in securing the future of AI!
We're seeking talented and passionate freelance AI Red Team experts to join our fight against potential AI vulnerabilities. If you live and breathe cybersecurity, and you're fascinated by the rapidly evolving world of AI, this is your chance to put your skills to the test and make a real impact.
The Mission (Should You Choose to Accept It): As an AI Red Teamer at LILT, you'll be on the front lines, adversarially testing our AI systems – including LLMs, multimodal models, inference services, RAG/embeddings, and product integrations. This isn't just about finding bugs; it's about thinking like an attacker, uncovering hidden weaknesses, and helping us build more robust and secure AI. Your Arsenal: Crafting clever prompts and scenarios to test model guardrails. Is This You? Key Qualifications: Generative AI Guru: Deep understanding of generative AI models, including their architectures, training (prompt engineering, fine-tuning, RLHF), and potential failure modes. Core
Exploring creative ways to bypass restrictions.
Systematically documenting your findings.
Collaborating with engineers and safety researchers to improve system defenses.
Cybersecurity & Threat Modeling Master: Proven experience in cybersecurity principles, threat modeling, vulnerability assessment, and penetration testing. You can identify attack vectors, simulate real-world threats, and understand the impact of an attack.
Data Analysis & NLP Ninja: Strong analytical skills to dissect model outputs, identify biases or factual errors, and recognize patterns. A background in Natural Language Processing (NLP) is a huge plus.
Ethical Hacking Mindset: A commitment to using your skills for defensive purposes, adhering to a strict ethical code, and understanding responsible disclosure.