AI Red Team Expert (Freelance) - Secure the Future of Language AI
Join LILT, a leader in AI-powered translation, and help us safeguard our cutting-edge language models. We're not just translating words; we're making information accessible to everyone, everywhere. To achieve this, we need to ensure our AI is robust, secure, and resistant to misuse. That's where you come in.
As a freelance AI Red Team Expert, you'll be a critical part of our security efforts, responsible for proactively identifying vulnerabilities and weaknesses in our AI systems. Think like an attacker, explore creative ways to bypass restrictions, and help us build more resilient and secure AI.
What You'll Do:
Conduct adversarial testing of AI systems, including LLMs, multimodal models, inference services, RAG/embeddings, and product integrations.
Craft compelling prompts and scenarios to test model guardrails and identify potential failure modes.
Systematically document testing outcomes and collaborate with engineers and safety researchers to improve system defenses.
Develop and maintain a deep understanding of generative AI models, their architectures, and training processes.
Simulate real-world threats and understand the potential impact of attacks.
Key Skills We're Looking For:
Generative AI Expertise: Deep understanding of generative AI models, including LLMs, their underlying architectures, training processes (including prompt engineering, fine-tuning, and RLHF), and potential failure modes.
Cybersecurity & Threat Modeling: Solid foundation in cybersecurity principles, threat modeling, vulnerability assessment, and penetration testing.
Data Analysis & NLP: Strong analytical skills to dissect model outputs, identify biases and errors, and recognize patterns. A background in Natural Language Processing (NLP) is a plus.
Ethical Hacking Mindset: Commitment to ethical and responsible security practices.
Core