Who we're looking for

Are you passionate about securing the next generation of AI systems? Do you thrive on identifying vulnerabilities, building defensive and offensive security modules, and leveraging AI-assisted development to accelerate your work? If so, we want to hear from you!

We are seeking a Security Engineer to prototype core security modules for our cybersecurity platform that tests and protects AI applications and Agents. You will collaborate closely with security researchers, developers, product teams, and Founders to create robust offensive and defensive security solutions that safeguard cutting-edge AI innovations.

Responsibilities

• Design, develop, and prototype security modules for testing and protecting AI Agents (offensive and/or defensive)
• Build and maintain core platform components focused on AI security assessment and defense
• Collaborate with research, product, and engineering teams to identify threats and develop countermeasures
• Leverage AI-assisted development tools and LLMs to accelerate security module prototyping
• Stay current on emerging AI security threats, attack vectors, and defense mechanisms
• Conduct security research and translate findings into actionable platform features

Background & Experience

• 5+ years of hands-on cybersecurity experience (offensive security, defensive security, or both)
• Programming skills with ability to develop functional prototypes and security tools
• Experience with AI-assisted development and research methodologies
• Bachelor's (or higher) degree in Cybersecurity, Computer Science, or a related field
• Demonstrated interest or experience in AI Security

Skills & Attributes

• Security-First Mindset: Deep understanding of attack vectors, vulnerabilities, and defense strategies
• Technical Versatility: Ability to code security tools, exploits, and defensive modules
• AI Enthusiasm: Passionate about the intersection of AI and cybersecurity
• Autonomy & Initiative: Ability to work independently and drive projects from concept to prototype
• Fast Learner: Quick to adapt to emerging AI security challenges and technologies

Additional Advantages

• Experience in red teaming, penetration testing, or vulnerability research
• Familiarity with AI/ML model security (adversarial attacks, prompt injection, model poisoning)
• Experience with agent frameworks and LLM security
• Background in secure software development practices
• Core Tech Stack: Python, Docker, and open-source security tools

Why join us?

• Play a key role in shaping the future of AI by protecting it
• Work alongside a diverse team of security researchers and industry experts—our founders are pioneers in AI Security and our Angels include top cyber experts like ex-CISO of Twitter
• Opportunity to innovate at the cutting edge of AI security research
• Significant equity compensation for early hires, professional growth, and an environment that fosters creativity and collaboration
• Unlimited access to all AI Tools and GPUs to run local LLMs