Join LILT as an AI Red Team Expert: Break Our AI Before Someone Else Does
At LILT, we're revolutionizing global communication with cutting-edge AI. We're seeking talented and motivated Freelance AI Red Team experts to help us fortify our AI systems against potential threats. If you're passionate about cybersecurity and have a knack for finding vulnerabilities, we want you on our team. Be part of a mission to make the world's information accessible to everyone.
The Mission: Your Role in AI Security
As an AI Red Team expert, you'll be at the forefront of adversarial testing, pushing our AI systems to their limits. You'll be working on:
LLMs (Large Language Models)
Multimodal Models
Inference Services
RAG/Embeddings (Retrieval-Augmented Generation)
Product Integrations
Your challenge: think like a malicious actor. Craft ingenious prompts, simulate real-world attacks, and uncover weaknesses in our AI defenses. You'll systematically document your findings and collaborate with engineers and safety researchers to harden our systems.
What You'll Do: Key Responsibilities
Develop and execute adversarial testing strategies against a range of AI systems.
Craft creative prompts and scenarios to bypass model guardrails and expose vulnerabilities.
Thoroughly document testing outcomes and provide actionable recommendations for improvement.
Collaborate with engineers and safety researchers to share findings and enhance system defenses.
Stay up-to-date on the latest AI security threats and vulnerabilities.
Are You the Right Person? Essential Skills
We're looking for someone with a strong foundation in both AI and cybersecurity. You should possess:
Deep Understanding of Generative AI: Grasp the inner workings of LLMs, multimodal models, and other AI systems, including their architectures, training processes, and potential failure modes. Familiarity with prompt engineering, fine-tuning, and Reinforcement Learning with Human Feedback (RLHF) is crucial.
Cybersecurity & Threat Modeling Expertise: Solid experience in cybersecurity principles, including threat modeling, vulnerability assessment, and penetration testing. You should be able to identify attack vectors, simulate real-world threats, and understand their potential impact.
Data Analysis & NLP Skills: Strong analytical skills to dissect model outputs, identify subtle biases or factual errors, and recognize patterns in model responses. A background in Natural Language Processing (NLP) is a significant advantage.
An Ethical Hacking Mindset: A commitment to using your skills for defensive purposes, 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 Proficiency: Advanced English (C1 or above).
Adversarial Thinking: A natural ability to think like an attacker.
Vulnerability Knowledge: Understanding of common model vulnerabilities (prompt injection, prompt-history leakage, data exfiltration via RAG).
AI/ML Security Experience: Proven experience in AI/ML security, evaluation, and red teaming, particularly with LLMs, AI agents, and RAG pipelines.
Adaptability: Eagerness to learn new methods, switch between tasks quickly, and work with complex guidelines.
Scripting Skills: Proficient in scripting and automation using Python, Bash, or PowerShell.
Familiarity with Frameworks: Experience with AI red-teaming frameworks such as garak or PyRIT.
Bonus Points: Preferred Skills
Physical-world adversarial testing experience.
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? The Perks
Competitive Pay: Earn up to $55/hour, depending on your skills, experience, and project needs.
Flexibility: Part-time, remote, freelance work that fits your schedule.
Impactful Work: Gain valuable experience on cutting-edge AI projects, enhancing your portfolio.
Real Influence: Help shape the future of AI and improve how models understand and communicate.
Behind the Code: Our Story
LILT was born from the frustration of our founders, former Google Translate engineers, with the limitations of existing enterprise translation solutions. They envisioned something better, a platform powered by AI and human expertise to make information accessible to everyone. Today, LILT is trusted by leading organizations like Intel, Canva, and the US Department of Defense.
Under the Hood: Our Tech
What sets LILT apart?
Brand-Aware AI: Learns your voice, tone, and terminology for accurate and consistent translations.
Agentic AI Workflows: Automates the entire translation process.
Extensive Integrations: 100+ native integrations with platforms like Adobe Experience Manager, Webflow, Salesforce, GitHub, and Google Drive.
Human-in-the-Loop: Global network of expert linguists for high-impact content review.
LILT in the Spotlight
Featured in The Software Report’s Top 100 Software Companies!
Ranked on the Inc. 5000 List.
Holding numerous patents for AI and language model innovations.
Stay updated with all our news.
If you're ready to take on the challenge of securing the future of AI, apply now and join the LILT team!