AI Red Team - Freelance Opportunity at LILT
Join LILT and defend the future of AI! We're revolutionizing global communication by making information accessible to everyone, regardless of language. We leverage cutting-edge AI, machine translation, and human-in-the-loop expertise, trusted by leading organizations like Intel, Canva, and the US Department of Defense. If you're passionate about AI security and ethical hacking, we want you on our team.
The Mission: As a freelance AI Red Team expert, you'll collaborate on adversarial testing projects, pushing the boundaries of AI system security. You'll focus on: LLMs (Large Language Models) Your challenge? Think like an attacker to uncover vulnerabilities and strengthen AI defenses. You'll craft ingenious prompts and scenarios, systematically documenting your findings and collaborating with engineers and safety researchers. What You'll Do: Develop and execute adversarial attacks against AI systems. Is This You? We're looking for individuals with: Key Skills: Deep Understanding of Generative AI: Including architectures, training processes, and failure modes (prompt engineering, fine-tuning, RLHF). Core
Multimodal models
Inference services
RAG/embeddings (Retrieval-Augmented Generation)
Product integrations
Test model guardrails and identify creative bypasses.
Document vulnerabilities and potential attack vectors.
Collaborate with engineers to improve system defenses.
Stay up-to-date on the latest AI security threats and techniques.
Cybersecurity & Threat Modeling: Experience in vulnerability assessment, penetration testing, and simulating real-world threats.
Data Analysis & NLP: Strong analytical skills to identify biases, factual errors, and patterns in model outputs. NLP background highly valued.
Ethical Hacking Mindset: Commitment to defensive security, ethical code adherence, and responsible disclosure.