AI Security Engineer - Red Team (United States, Remote)

📋 Description

• • As an AI Security Engineer on our Red Team, you will be at the vanguard of a rapidly evolving field, tasked with pushing the boundaries of artificial intelligence security and safety. This role is designed for individuals who are passionate about tackling nascent problems, possess a strong desire to innovate, and excel in both deconstructing complex systems and architecting scalable processes.
• • You will lead cutting-edge security assessments of AI systems, focusing on both established and emerging modalities. This includes, but is not limited to, text-based Large Language Model (LLM) applications, as well as more complex multimodal agentic systems that integrate various forms of data and interaction.
• • A core aspect of your responsibility will be the development of novel testing methodologies and tooling. You will build upon our existing frameworks and playbooks, enhancing them to ensure consistent, high-quality service delivery as we scale our AI red teaming capabilities. This involves identifying and automating tedious, repetitive tasks to increase team efficiency and effectiveness.
• • This is a highly cross-functional position where you will work directly with enterprise clients. Your engagement will span the entire lifecycle of security assessments, from initial project scoping and defining testing requirements to establishing clear success criteria and delivering actionable insights.
• • You will conduct comprehensive security assessments, meticulously analyzing AI systems for vulnerabilities. This includes a deep dive into known LLM weaknesses such as prompt injection, data poisoning, and jailbreaking techniques, as well as exploring new attack vectors relevant to multimodal and agentic AI.
• • A significant part of your role will involve translating your findings into comprehensive security assessment reports. These reports will not only detail the vulnerabilities discovered but also provide clear, actionable recommendations for remediation. You will be responsible for presenting these findings and strategic recommendations to both technical teams and executive stakeholders, ensuring a clear understanding of risks and mitigation strategies.
• • Beyond client delivery, you will be instrumental in the research and innovation arm of our AI security efforts. This involves staying abreast of the latest AI security threats, attack vectors, and defense mechanisms. You will translate cutting-edge academic research and industry trends into practical, effective testing approaches.
• • Collaboration is key. You will work closely with our research and product teams to continuously refine and elevate our methodologies, ensuring Lakera remains at the forefront of AI security innovation.
• • This role offers a unique opportunity to apply your traditional cybersecurity expertise to the new frontier of AI security and safety. You will be instrumental in defining best practices and shaping the future of this critical discipline.
• • Key responsibilities include leading end-to-end AI red teaming engagements, collaborating with clients on project scope and requirements, conducting thorough security assessments of AI systems (LLMs, multimodal agents), authoring detailed reports with actionable findings, and presenting findings to stakeholders.
• • You will also be responsible for developing and improving processes, playbooks, and tooling to scale service delivery, automating repetitive tasks to enhance team efficiency, and researching novel red teaming methodologies for emerging AI modalities like image, video, audio, and autonomous systems.
• • Furthermore, you will stay ahead of the curve on AI security threats and translate research into practical testing approaches, collaborating with internal teams to continuously improve our offerings.
• • This position is ideal for someone who thrives in ambiguity, enjoys building solutions from the ground up, and is eager to make a significant impact in a rapidly growing and critical area of technology.
• • Your work will directly contribute to the security and trustworthiness of AI systems used by leading enterprises, ensuring responsible AI development and deployment.
• • You will gain invaluable experience in a highly sought-after specialization, working with state-of-the-art AI technologies and contributing to the foundational principles of AI security.
• • The role demands a blend of offensive security skills, analytical thinking, strong communication, and a proactive approach to problem-solving in a dynamic environment.
• • You will be empowered to innovate, experiment, and lead initiatives that define the future of AI security assessments and client services.
• • This is more than just a job; it's a chance to be a pioneer in securing the next generation of intelligent systems.