Unleash Your Inner Hacker: AI Red Team Experts Wanted
LILT is revolutionizing how the world communicates using cutting-edge AI. We're not just building machine translation; we're making global information accessible to everyone. Join us in our mission to break AI and build it back stronger!
We're seeking skilled and passionate Freelance AI Red Team experts to join our fight on the front lines. You'll be tasked with pushing the limits of our AI systems, identifying vulnerabilities, and helping us build more robust and secure AI for a global audience. Think like an adversary, exploit weaknesses, and shape the future of AI safety.
What You'll Do
Conduct adversarial testing of AI systems, including LLMs, multimodal models, inference services, RAG/embeddings, and product integrations.
Craft ingenious prompts and scenarios to bypass model guardrails and uncover hidden weaknesses.
Systematically document findings and collaborate with engineers and safety researchers to improve system defenses.
Think outside the box to identify novel attack vectors and potential real-world threats.
Is This You?
If you get excited about breaking things to make them better, and you have a solid background in both cybersecurity and AI, this could be the perfect opportunity. Here's what we're looking for:
Key Skills
Generative AI Expertise: Deep understanding of Generative AI and main models, including their underlying architectures, training processes (including prompt engineering, fine-tuning, and RLHF), and potential failure modes.
Cybersecurity & Threat Modeling: Proven experience in cybersecurity principles, threat modeling, vulnerability assessment, and penetration testing. You can identify attack vectors, simulate real-world threats, and understand the potential impact of an attack.
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: A commitment to ethical and security-focused practices, adhering to a strict ethical code, and understanding responsible disclosure.
Core Requirements
Education: Bachelor's or Master’s Degree in Computer Science, Software Engineering, Cybersecurity, Digital Forensics, or a related field.
Language: Advanced English proficiency (C1 or above).
Mindset: A true adversarial thinker with a passion for uncovering vulnerabilities.
Knowledge: Solid understanding of common model vulnerabilities, including prompt injection, prompt-history leakage, and data exfiltration via RAG.
Experience: Hands-on experience in AI/ML security, evaluation, and red teaming, particularly with LLMs, AI agents, and RAG pipelines.
Adaptability: Ability to quickly learn new methods, switch between tasks, and work with complex guidelines.
Scripting: Proficient in scripting and automation using Python, Bash, or PowerShell.
Frameworks: Familiarity with AI red-teaming frameworks such as garak or PyRIT.
Bonus Points (Preferred Requirements)
Experience with physical-world adversarial testing.
Experience with containerization and CI/CD security tools, especially Docker.
Proficiency in offensive exploitation and exploit development.
Skilled in reverse engineering using tools like Ghidra or equivalents.
Expertise in network and application security, including web application security.
Knowledge of operating system security concepts such as Linux privilege escalation and Windows internals.
Familiarity with secure coding practices for full-stack development.
Why LILT?
Competitive Rates: Get paid up to $55/hour based on your skills, experience, and project demands.
Flexibility: Work part-time, remotely, and on a freelance basis – perfect for fitting around your existing commitments.
Impact: Work on cutting-edge AI projects and build your portfolio.
Innovation: Influence how future AI models understand and communicate across languages and cultures.
Join Our Story
Our founders, Spence and John, met at Google working on Google Translate, driven by a shared vision: to make information universally accessible. Dissatisfied with the status quo, they built LILT to raise the bar for AI-powered language translation. LILT has been a machine learning company since day one. Now, with AI innovation accelerating, we're leading the way in the next phase of AI-driven communication.
Our Tech
What sets LILT apart?
Brand-Aware AI: AI that learns your voice, tone, and terminology for accurate and consistent translations.
Agentic AI Workflows: Automate the entire translation process, from content ingestion to quality review.
Seamless Integrations: 100+ native integrations with platforms like Adobe Experience Manager, Webflow, Salesforce, and GitHub.
Human-in-the-Loop: Access our global network of expert linguists for high-impact content.