We're looking for an AI Security Engineer to join our Red Team and help us push the boundaries of AI security.
You'll run cutting-edge security assessments, develop novel testing methodologies, and work directly with enterprise clients to secure their AI systems. This role combines hands-on manual and automated red teaming, client engagement, and the development of automation that helps scale testing efforts. You'll thrive in this role if you want to be at the forefront of an emerging discipline, enjoy working on nascent problems, and like both breaking things and building processes that scale.
This is a highly cross-functional position. AI security is still being defined, with best practices emerging in realtime. You'll be building the frameworks, methodologies, and tooling that scale our services while staying adaptable to rapid changes in the AI landscape. This role is ideal for someone who wants to take their traditional cybersecurity expertise and apply it to the new frontier of AI security and safety. Your focus will span several key areas:
Service Delivery & Client Engagement
- Deliver AI red teaming security assessments for enterprise customers.
- Collaborate with clients to scope projects, define testing requirements, and establish success criteria
- Conduct comprehensive security assessments of AI systems, including text-based LLM applications and multimodal agentic systems
- Extend testing to tools, APIs, and services these AI systems connect to
- Test manually and creatively beyond automated coverage to find the failures that tooling misses
- Author detailed security assessment reports with actionable findings and remediation recommendations
- Present findings and strategic recommendations to technical and executive stakeholders through report readouts and Q&A sessions
Tooling & Methodology Development
- Build upon and improve our established processes and playbooks to scale AI red teaming service delivery
- Develop frameworks to ensure consistent, high-quality service delivery
- Find tedious, repetitive tasks and automate them. You don't need to be a world-class developer—just someone who can build tools that make the team more effective. The goal is to automate routine work to free up time for targeted manual testing, not replace it.
Research & Innovation
- Develop novel red teaming methodologies for emerging modalities: image, video, audio, autonomous systems
- Stay ahead of the latest AI security threats, attack vectors, and defense mechanisms
- Translate cutting-edge academic and industry research into practical testing approaches
- Collaborate with our research and product teams to continuously level up our methodologies
Technical Expertise
- Demonstrated offensive security experience shown through red teaming, penetration testing, security assessments, bug bounty programs, and/or CTF participation
- Demonstrated ability to find and exploit real vulnerabilities by hand, not only by running tools
- Strong knowledge of web application, API, and network security fundamentals
- Deep understanding of LLM vulnerabilities including direct and indirect prompt injection, jailbreaking, data poisoning, agentic and tool-use risks
- Practical experience with threat modeling complex systems and architectures
- Proficiency in developing automated tooling to enable and enhance testing capabilities, improve workflows, and deliver deeper insights
Professional Skills
- Proven track record of contributing to or leading client-facing security assessment projects from scoping through delivery
- Excellent technical writing skills with experience creating executive-level security reports
- Strong presentation and communication skills, with the ability to clearly explain assessment findings and answer customer questions.
- Experience or interest building processes, documentation, and tooling for service delivery teams
AI Security Knowledge
- Understanding of AI/ML model architectures, training processes, and deployment patterns
- Familiarity with AI security frameworks such as the OWASP Top 10 for LLM Applications, the OWASP
- Top 10 for Agentic Applications, and MITRE ATLAS.
- Knowledge of emerging AI attack surfaces including multimodal systems and AI agents, and the tool and Model Context Protocol (MCP) integrations around them
Preferred Qualifications
- Relevant security certifications (OSCP, OSWA, OSAI, COAE, BSCP, etc.)
- Professional web application, API, or network penetration testing experience
- Hands-on experience performing AI red teaming assessments, with a strong plus for experience targeting agentic systems
- Demonstrated experience designing LLM jailbreaks
- Active participation in security research and tooling communities
- Background in threat modeling and risk assessment frameworks
- Previous speaking experience at security conferences or industry events
What You'll Gain
- Opportunity to shape the future of AI security as an emerging discipline
- Work with cutting-edge AI technologies and novel attack methodologies
- Lead high-visibility projects with enterprise clients across diverse industries
- Collaborate with a world-class research team pushing the boundaries of AI safety
- Research and development time between engagement cycles to contribute to team success
- Platform to establish thought leadership within the AI security community
All your information will be kept confidential according to EEO guidelines.