AI Security Engineer

Summary

Join SentinelOne, a leading cybersecurity company, as a Staff AI Security Engineer. You will be responsible for safeguarding AI systems, particularly large language models (LLMs), from adversarial attacks. Your role will involve conducting red teaming exercises, developing security measures, collaborating with cross-functional teams, staying updated on AI security advancements, and mentoring junior engineers. This position requires a strong background in AI and offensive security research, including experience with prompt injection, jailbreaking, and model manipulation. You will also need to be proficient in Python programming and AI/ML frameworks.

Requirements

• A degree in Computer Science, Cybersecurity, Artificial Intelligence, or a related field, or equivalent practical experience
• 7+ years of experience in cybersecurity, with recent and strong experience in AI systems and large language models
• Proven experience in conducting red teaming exercises on LLMs, including techniques such as prompt injection, jailbreaking, and model manipulation
• Strong understanding of frameworks and tools related to AI security, such as OWASP's guidelines for LLM security and Microsoft's Prompt Shields
• Hands-on experience with adversarial attack simulation frameworks and vulnerability assessment tools specific to AI models
• Excellent problem-solving skills, creativity, and self-motivation, with the ability to work independently and as part of a team
• Strong programming skills in Python and familiarity with AI/ML frameworks.  Ability to automate and use AI as a developer
• Exceptional communication skills, with the ability to convey complex security concepts to diverse audiences

Responsibilities

• Conduct comprehensive red teaming exercises on LLM-based products to uncover and address vulnerabilities related to prompt injection, jailbreaking, and unauthorized data extraction
• Develop and implement advanced security measures to protect AI products from adversarial manipulations and ensure compliance with responsible AI practices
• Collaborate with cross-functional teams, including AI researchers, engineers, and product managers, to integrate security best practices into the AI development lifecycle
• Stay abreast of the latest research and developments in AI security, contributing to the continuous improvement of our security posture
• Mentor and guide junior engineers, fostering a culture of security awareness and proactive defense strategies within the organization

Preferred Qualifications

• Contributions to or development of guarding or attacking generative AI systems
• Experience with offensive security research, including penetration testing and exploit development
• Familiarity with regulatory and compliance standards related to AI and data security
• Contributions to the cybersecurity community through research publications, conference presentations, or open-source projects

Benefits

• Medical, Vision, Dental, 401(k), Commuter, Health and Dependent FSA
• Unlimited PTO
• Industry-leading gender-neutral parental leave
• Paid Company Holidays
• Paid Sick Time
• Employee stock purchase program
• Disability and life insurance
• Employee assistance program
• Gym membership reimbursement
• Cell phone reimbursement
• Numerous company-sponsored events, including regular happy hours and team-building events