Join LILT as an AI Red Team Expert: Break Our AI (Before Someone Else Does!)
AI is revolutionizing communication, and LILT is at the forefront. We're driven by a mission to make the world's information accessible to everyone, regardless of language. We're not just talking about basic translation – we're building a category-defining company by leveraging cutting-edge AI, machine translation, and human-in-the-loop expertise to deliver translations that are faster, more accurate, and cost-effective, all while maintaining brand integrity and quality.
We need sharp minds to help us fortify our AI systems. That's where you come in.
The Mission: AI Red Team (Freelance)
As a freelance AI Red Team expert, you'll be on the front lines, collaborating on projects focused on adversarial testing of our AI systems. We're talking LLMs, multimodal models, inference services, RAG/embeddings, and deep product integrations. This isn't your average security gig; you'll be:
Crafting ingenious prompts and scenarios to push our model guardrails to their absolute limits.
Thinking like an adversary to discover creative ways to bypass restrictions and uncover hidden weaknesses.
Systematically documenting your findings and collaborating with our engineers and safety researchers to improve our defenses.
Essentially, you'll be a professional AI hacker, helping us stay one step ahead of potential threats.
Is This You? Key Qualifications
We're looking for someone who:
Lives and breathes Generative AI: Deep understanding of Generative AI models (especially LLMs), including their architectures, training processes, and potential failure modes. You're fluent in prompt engineering, fine-tuning, and reinforcement learning with human feedback (RLHF).
Speaks Cybersecurity fluently: Proven experience in cybersecurity principles, including threat modeling, vulnerability assessment, and penetration testing. You can identify attack vectors, simulate real-world threats, and understand their potential impact.
Is a Data Whisperer: 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 major plus.
Has an Ethical Hacking Mindset: Unwavering commitment to using your skills for defensive and security-focused purposes, adhering to a strict ethical code, and understanding responsible disclosure.
Core Requirements (Must-Haves)
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: Strong adversarial thinking – you enjoy finding weaknesses.
Knowledge: Solid understanding of common model vulnerabilities (prompt injection, prompt-history leakage, 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: Ready to learn new methods, switch between tasks quickly, and work with complex guidelines.
Scripting Prowess: Proficient in scripting and automation using Python, Bash, or PowerShell.
Framework Familiarity: Familiar with AI red-teaming frameworks such as garak or PyRIT.
Bonus Points (Preferred Qualifications)
Experience with physical-world adversarial testing.
Expertise in containerization and CI/CD security tools (Docker).
Proficiency in offensive exploitation and exploit development.
Skills in reverse engineering (Ghidra or similar tools).
Expertise in network and application security, including web application security.
Knowledge of operating system security concepts (Linux privilege escalation, Windows internals).
Familiarity with secure coding practices for full-stack development.
The Perks of the Mission
Why should you join our Red Team?
Competitive Pay: Earn up to $55/hour, based on your skills, experience, and project needs.
Flexibility: Part-time, remote, freelance work that fits your existing commitments.
Cutting-Edge Experience: Work on advanced AI projects and build a killer portfolio.
Real Impact: Directly influence how future AI models understand and communicate.
Our Story: From Google Translate to AI-Powered Translation
LILT was born from a desire to improve upon existing translation technology. Our founders, Spence and John, met at Google working on Google Translate. They realized the existing solutions weren't good enough for enterprise use, so they set out to build something better. Since 2015, LILT has been a machine learning company dedicated to pushing the boundaries of AI-powered translation.
We're backed by Sequoia, Intel Capital, and Redpoint, and we're trusted by industry leaders like Intel, Canva, the United States Department of Defense, and ASICS. We're not just translating words; we're connecting people and cultures.
Our Tech: AI That Understands Your Brand
What makes LILT different?
Brand-Aware AI: Learns your unique voice, tone, and terminology for consistent and accurate translations.
Agentic AI Workflows: Automate the entire translation process, from content ingestion to quality review and publishing.
Seamless Integrations: 100+ native integrations with systems like Adobe Experience Manager, Webflow, Salesforce, GitHub, and Google Drive.
Human Expertise: Human-in-the-loop reviews by our global network of professional linguists for high-impact content.
LILT in the News
Featured in The Software Report’s Top 100 Software Companies!
LILT makes it onto the Inc. 5000 List.
LILT’s continues to be an intellectual powerhouse, holding numerous patents that help power the most efficient and sophisticated AI and language models in the industry.
Check out all our news on our website.
Information collected and processed as part of your application process, including any job applications you choose to submit, is subject to LILT's Privacy Policy at https://lilt.com/legal/privacy.
At LILT, we are committed to a fair, inclusive, and transparent hiring process. As part of our recruitment efforts, we may use artificial intelligence (AI) and automated tools to assist in the evaluation of applications, including résumé screening, assessment scoring, and interview analysis. These tools are designed to support human decision-making and help us identify qualified candidates efficiently and objectively. All final hiring decisions are made by people. If you have any concerns, require accommodations, or would like to opt-out of the use of AI in our hiring process, please let us know at [email protected].
LILT is an equal opportunity employer. We extend equal opportunity to all individuals without regard to an individual’s race, religion, color, national origin, ancestry, sex, sexual orientation, gender identity, age, physical or mental disability, medical condition, genetic characteristics, veteran or marital status, pregnancy, or any other classification protected by applicable local, state or federal laws. We are committed to the principles of fair employment and the elimination of all discriminatory practices.