AI Red Team - Freelance Opportunity at LILT
Ready to break things? Join LILT, a leader in AI-powered translation, and help us fortify our AI systems against emerging threats. We're seeking skilled and creative AI Red Team experts to help us secure our Large Language Models (LLMs), multimodal models, inference services, RAG/embeddings, and product integrations.
At LILT, we're on a mission to make the world's information accessible to everyone. We use cutting-edge AI, machine translation, and human-in-the-loop expertise to translate content faster, more accurately, and more cost-effectively. As part of our security team, you'll play a critical role in ensuring the safety and reliability of our AI-powered platform.
What You'll Do
Think like an adversary: Craft innovative prompts and scenarios to test model guardrails and bypass restrictions.
Uncover weaknesses: Identify and document vulnerabilities in our AI systems.
Collaborate with experts: Share your findings with engineers and safety researchers to improve system defenses.
Stay ahead of the curve: Research and experiment with new attack techniques and security methodologies.
What You'll Bring
Key Skills
Generative AI Expertise: Deep understanding of Generative AI, including LLMs, their architectures, training processes, and potential failure modes (prompt engineering, fine-tuning, RLHF).
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 and identify biases or errors. A background in Natural Language Processing (NLP) is highly beneficial.
Ethical Hacking Mindset: Commitment to using your skills for defensive purposes and adhering to a strict ethical code.
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).
Adversarial thinking
Knowledge of vulnerabilities, including common model vulnerabilities (prompt injection, prompt-history leakage, data exfiltration via RAG).
Experience in AI/ML security, evaluation, and red teaming, particularly with LLMs, AI agents, and RAG pipelines.
Adaptability and a passion for learning new methods in a fast-paced environment.
Proficiency in scripting and automation using Python, Bash, or PowerShell.
Familiarity with AI red-teaming frameworks such as garak or PyRIT.
Bonus Points
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?
Competitive Rates: Earn up to $55/hour based on your skills, experience, and project needs.
Flexible Schedule: Part-time, remote, freelance work that fits your commitments.
Cutting-Edge Projects: Gain valuable experience working on advanced AI projects.
Meaningful Impact: Influence how future AI models understand and communicate.
About LILT
LILT was founded by former Google Translate engineers, Spence Green and John DeNero, who saw an opportunity to improve the quality of enterprise translation using AI. Backed by Sequoia, Intel Capital, and Redpoint, we’re building a category-defining company in a $50B+ global translation market being redefined by AI.
Our values: Work together, win together; Find a way or make one; Quicker than they expect; Quality is Job 1.
Our Tech
What sets our platform apart:
Brand-aware AI that learns your voice, tone, and terminology.
Agentic AI workflows that automate the entire translation process.
100+ native integrations with systems like Adobe Experience Manager, Webflow, Salesforce, GitHub, and Google Drive.
Human-in-the-loop reviews via our global network of professional linguists.
Ready to Join the LILT Team?
If you're a passionate cybersecurity professional with a knack for breaking things, we encourage you to apply! Help us build a more secure and accessible world through the power of AI.