THE ROLE:
Information Security Manager, AI Red Team Lead will be responsible for developing an AI Red Teaming capability (focusing on people, process, and technologies) and leading AI Red Teaming engagements. The AI Red Team lead will develop and execute Offensive Security tactics and techniques to identify and exploit security vulnerabilities in AMD’s AI systems and develop/support appropriate remediation. The individual will work with AI developers to educate and implement guardrails throughout the AI pipeline to mitigate AI model attacks. The lead will work with AMD’s Enterprise Security Architecture (ESA), Security Operations Center (SOC), Security Engineering and Governance, Risk and Compliance (GRC) functions to ensure AI security capabilities, security requirements, and relevant capabilities and detections are embedded into Information Security and business processes and technology requirements.
THE PERSON:
The ideal candidate will possess strong multi-tasking skills and enthusiasm for details and should think one step ahead of cyber-criminals. They should be well prepared to thrive in a fast-paced environment, possessing strong interpersonal and communication skills. You will use your critical thinking and sense of ownership to focus on long term quality IT security solutions. Are you self-motivated and a team player with proven ability to deliver end-to-end solutions in a high-tech and fast-moving industry? If so, this is a great career opportunity!
KEY RESPONSIBILITIES:
- Lead Offensive Security engagements to simulate adversarial AI attacks and drive defensive security controls for AMD’s AI use and development.
- Perform evaluations and testing in a manner that is responsible, ethical and in compliance with established AMD security policies and standards.
- Work with business teams to scope, document, execute testing and drive remediation for AI Red Teaming engagements.
- Work with industry partners to incorporate learnings and emerging AI tactics, techniques, and procedures (TTPs) into AMD’s AI Red Teaming engagements to develop comprehensive AI testing and evaluation processes, procedures and standards.
- Collaborate with AMD’s Responsible AI team(s) leveraging AI research, regulatory requirements and industry-prescribed AI Red Teaming procedures and security frameworks.
- Provide business context to emerging AI security threats, tactics, and techniques to drive AI developer awareness and diligence.
- Work with AMD’s SOC to continuously measure, validate and improve AMD’s security defense capabilities.
- Contribute to AMD’s AI efforts by supporting the development of AI Red Teaming presentations, standard operating procedures, and training materials for AI teams to ensure AI security and safety testing is conducted throughout AI pipeline development.
- Implement automation strategies for conducting AI Red Teaming to support AMD’s AI developer community.
- Provide inputs into AMD’s AI security strategy, AI security controls framework and relevant procedures.
- Support business and AI technology owners in identifying potential security threats to AMD AI systems and data to determine appropriate security measures.
- Advise on system and model security designs and controls and recommend security enhancements
- Lead executive-level security communications and presentations.
- Build and maintain strong, collaborative working relationships and trust with key stakeholders across business units and corporate areas.
- Lead and mentor team of junior application penetration testers.
PREFERRED EXPERIENCE:
- Extensive experience in application security, penetration testing and Offensive Security technologies for network, application including AI penetration testing (AI/ML experience preferred)
- Proficiency in offensive and defensive security architectures and controls.
- Python programming
- Experience in AI/ML model development, engineering, data science and data pre-processing (preferred but not required)
- Have working knowledge of AI Information Security frameworks/standards (NIST AI RMF, OWASP, MITRE ATLAS)
- Must maintain knowledge of latest security regulations, AI security publications, trends and TTPs
- Must be familiar with enterprise security technologies
- Problem solving ability and strong analytical skills
- Able to effectively communicate, interact and influence business stakeholders
- Ability to deliver innovative solutions and consistently demonstrate business-focused outcomes
- Possess strong communication skills (both written and verbal)
- Possess strong interpersonal skills and ability to adapt information based on the audience
- Recognize and communicate potential security risks in a timely manner
- Be highly organized and self-reliant, with the ability to multi-task
ACADEMIC CREDENTIALS:
- Have a bachelor’s degree or equivalent in Data Science, Computer Science, Information Security, Information Technology, Information Systems Management, or related field
LOCATIONS:
San Jose OR Austin
#LI-MF2
#LI-HYBRID
Qualifications:AMD does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. AMD and its subsidiaries are equal opportunity, inclusive employers and will consider all applicants without regard to age, ancestry, color, marital status, medical condition, mental or physical disability, national origin, race, religion, political and/or third-party affiliation, sex, pregnancy, sexual orientation, gender identity, military or veteran status, or any other characteristic protected by law. We encourage applications from all qualified candidates and will accommodate applicants’ needs under the respective laws throughout all stages of the recruitment and selection process.