AI Offensive Security Engineer

The Cyber Security Offensive Security analyst will be responsible for building out the capability for our team to conduct operations using natural language processing and large language models to enhance Microns internal and external penetration testing. The analyst will also work with other teams to transfer knowledge pertaining to current exploitation tools, techniques, and procedures as well as active threat groups to enhance defensive cyber security operations. In addition, Micron’s Offensive Security team works with key stakeholders to identify technology solutions to further augment our cyber security posture and mitigate risk from attack vectors.

A successful candidate for this position will have: 

• A strong focus on analytical approach 

• Significant expertise leading and participating in internal and external offsec operations 

• Extensive experience with computer and networking technologies, including the ability to evaluate proposed architecture designs and identify vulnerabilities and gaps in secure design principles 

• Expertise related to Machine Learning (ML) and Large Language Models (LLMs) in both concept and adversarial attacks 

• Python, C#, Go, and/or other programming languages 

• Knowledge of evasion techniques for endpoint and network security controls 

• Strong understanding of cloud environments and attacks 

• Proficiency in collaborating with teams across various functions to successfully achieve business objectives. 

• Strong presentation and communication skills especially around high technical subjects, and presenting to non-technical audiences 

• Ability to adapt to a fast paced and quickly changing environment 

Responsibilities will include, but are not limited to, the following: 

• Discover and exploit vulnerabilities end-to-end to assess the security of AI or AI adjacent systems 

• Implement Red Team operations on production AI systems, using real-world adversarial tactics and techniques to identify areas for improvement. 

• Keep abreast of current trends in AI threats and assist in creating counter strategies to minimize risk from AI exploitation.  

• Collaborate with teams to influence measurement and mitigations of these vulnerabilities in AI systems 

• Participate in broader red team activities, including web applications, security controls, network infrastructure, wireless, and mobile deployments, to identify and exploit weaknesses in organizational defenses 

• Work as a team to meet operational objectives while avoiding detection 

• Plan, carry out, lead, and report on testing activities and outcomes 

• Offensive security tooling and development, including creation of scripts and debugging proof of concept code to leverage in campaigns 

• Stay updated on the latest trends, techniques, and tools in AI security and red teaming. Continuously innovate and refine testing methodologies to keep pace with the evolving threat landscape