Join LILT as an AI Red Team Expert: Secure the Future of AI
Are you a cybersecurity professional with a passion for breaking things to make them stronger? LILT is seeking talented and motivated freelance AI Red Team experts to help us secure the next generation of AI. As AI reshapes global communication, we're at the forefront, ensuring its safety and reliability. If you're ready to dive deep into the world of adversarial AI testing, we want to hear from you.
About LILT: AI-Powered Translation for a Global World
LILT is revolutionizing how the world communicates by leveraging cutting-edge AI, machine translation, and human-in-the-loop expertise. Our mission is to make information accessible to everyone, regardless of language. Trusted by industry leaders like Intel, Canva, the U.S. Department of Defense, and ASICS, we're backed by Sequoia, Intel Capital, and Redpoint, and are building a category-defining company in the $50B+ global translation market.
The Opportunity: Become an AI Adversary
As a freelance AI Red Team expert, you'll be on the front lines, conducting adversarial testing on our AI systems, including LLMs, multimodal models, inference services, RAG/embeddings, and product integrations. You'll be responsible for:
Crafting ingenious prompts and scenarios to probe model guardrails.
Exploring creative bypasses to uncover vulnerabilities.
Systematically documenting your findings.
Collaborating with engineers and safety researchers to improve system defenses.
Think like an attacker, act like a defender. Your insights will directly impact the security and robustness of our AI-powered translation platform.
What You'll Need to Succeed
We're looking for individuals with a strong foundation in both cybersecurity and AI. Here's what we're looking for:
Key Criteria:
Deep Understanding of Generative AI: Including architectures, training processes (prompt engineering, fine-tuning, RLHF), and potential failure modes of main models.
Cybersecurity & Threat Modeling Expertise: Experience in threat modeling, vulnerability assessment, and penetration testing. Ability to identify attack vectors and simulate real-world threats.
Data Analysis & NLP Skills: Strong analytical abilities to dissect model outputs, identify biases or errors, and recognize patterns. A background in Natural Language Processing (NLP) is a plus.
Ethical Hacking Mindset: A commitment to ethical security practices and responsible disclosure.
Core