AI Security Researcher

About Us:

At Prompt Security, our mission is to empower organizations to safely harness the transformative power of Generative AI. As a one-stop security platform, we provide visibility, governance, and real-time protection against all GenAI concerns, enabling organizations to innovate and prosper in the age of AI without compromising on security.

As the GenAI security field continues to expand, Prompt Security is at the forefront of this revolution. This market’s rapid growth demands agility and flexibility from our team. As an AI Security Researcher, you’ll navigate an exciting landscape where innovation is constant, working on the frontline to develop and refine our security engine.

What we’re looking for:

We’re looking for someone who thrives in fast-paced environments, with a deep technical understanding of security issues and ready to to discover vulnerabilities in generative AI models and their underlying infrastructures. You will work collaboratively to develop proactive strategies that ensure our AI models remain robust, secure, and prepared for the future. If you’re passionate about staying ahead in a dynamic market and possess the skills and agility to keep pace with its evolution, Prompt Security is your arena to shine.

What you will do:

• Conduct advanced research to identify vulnerabilities within generative AI models and their infrastructures.
• Innovate and design cutting-edge techniques to circumvent existing AI security mechanisms.
• Assess and strengthen the security posture of AI systems, identifying weaknesses while collaborating with teams to implement actionable improvements.
• Partner with cross-functional teams to automate security testing processes and establish best practices for AI security.
• Publish papers and marketing content on research findings
• Stay informed about emerging trends in AI security, ethical hacking, and cyber threats to ensure Prompt Security remains a leader in the field.
  
  

• 3+ years of experience in offensive cybersecurity, with a strong focus on web applications and API security.
• Proficiency in programming and scripting languages relevant to AI security, including but not limited to Python and JavaScript.
• Deep understanding of AI technologies, particularly GenAI tools
• Comprehensive knowledge of AI vulnerabilities and effective mitigation strategies.
• Exceptional problem-solving, analytical, and communication skills that foster collaboration.