Join LILT as an AI Red Team Expert (Freelance)
Ready to break AI? LILT needs you. We're on a mission to make information accessible to everyone, leveraging cutting-edge AI and human expertise to revolutionize translation. We're seeking talented and passionate cybersecurity professionals to join us as freelance AI Red Team experts and help us secure the next generation of AI.
At LILT, you'll be pushing the boundaries of AI security, working on exciting projects and collaborating with a world-class team. If you're driven by curiosity, thrive on challenges, and have a knack for finding vulnerabilities, this is the perfect opportunity to make a real impact.
What You'll Do: As an AI Red Team Expert, you'll be at the forefront of adversarial testing for our AI systems, including: Large Language Models (LLMs) Your mission? Think like an attacker. You'll craft ingenious prompts and scenarios to test model guardrails, discover creative ways to bypass restrictions, and meticulously document your findings. You'll collaborate closely with our engineers and safety researchers to share your insights and fortify our system defenses. What We're Looking For: We're seeking individuals with a blend of cybersecurity expertise and a deep understanding of AI. Here's what we consider critical: Key Skills: Generative AI Expertise: Deep understanding of Generative AI models, including architectures, training processes (prompt engineering, fine-tuning, RLHF), and potential failure modes. Core
Multimodal Models
Inference Services
RAG/Embeddings
Product Integrations
Cybersecurity & Threat Modeling: Experience in cybersecurity principles, threat modeling, vulnerability assessment, and penetration testing. Ability to identify attack vectors and simulate real-world threats.
Data Analysis & NLP: Strong analytical skills to dissect model outputs, identify subtle biases or factual errors, and recognize patterns. A background in Natural Language Processing (NLP) is a plus.
Ethical Hacking Mindset: Commitment to using your skills defensively, adhering to a strict ethical code, and understanding responsible disclosure.