Senior AI Security R&D Engineer (Onsite)

Sandia National Laboratories; New Mexico; On-site; USD 117,500 - 235,700; Full time

Job summary

Sandia National Laboratories invites applications for a Senior/Principal R&D Cybersecurity role focused on Artificial Intelligence. You will work onsite on multidisciplinary teams across embedded to cloud environments, developing protective AI technologies, threat assessments, and robust security practices.

Key responsibilities include reverse engineering, firmware research, and designing new analysis methods.

Qualifications

• Bachelor's degree with five years directly relevant experience or equivalent.
• Ability to obtain and maintain a DOE Q and SCI clearance (polygraph possible).
• Experience in AI/ML security, vulnerabilities, and vulnerability research.
• Proficiency in Python, C/C++, and scripting.

Responsibilities

• Develop state-of-the-art approaches for analyzing AI system security and robustness.
• Analyze vulnerabilities in AI systems and how attackers may exploit them.
• Reverse engineer malicious code to support high-impact customers.
• Conduct low-level firmware research and analyze device software, hardware, and protocols.
• Design and develop new analysis methods and tools for AI security.
• Identify emerging AI threats and engage with the security community.
• Evaluate tools and processes used by AI security researchers to improve effectiveness.
• Develop thought models, tools, and datasets that characterize AI threats and vulnerabilities.
• Identify opportunities to apply AI to enhance cybersecurity research.

Skills

AI cybersecurity

Python

C/C++

Adversarial ML

Education

Bachelor's degree in a relevant discipline

Graduate degree in CS/Engineering or related field

Tools

Ghidra

IDA Pro

NumPy

PyTorch

TensorFlow

Job description

Sandia National Laboratories invites applications for a Senior/Principal R&D Cybersecurity role focused on Artificial Intelligence. You will work onsite on multidisciplinary teams across embedded to cloud environments, developing protective AI technologies, threat assessments, and robust security practices.

Key responsibilities include reverse engineering, firmware research, and designing new analysis methods.