Senior AI Red Team Engineer (ML Security)

Lockheed Martin; Shelton (NE); On-site; USD 136,000 - 252,000; Full time

Benefits offered by this job

Medical benefits

Dental benefits

Vision benefits

Flexible work arrangements

401(k) match

Job summary

Lockheed Martin is seeking an AI engineer with a strong background in AI/ML to join the AI Center. You will design and lead Red Team assessments of AI systems, exploring adversarial risks and governance, and work with developers, data scientists, platform engineers, and cybersecurity teams to build secure, trustworthy systems.

This role offers opportunities to lead projects and teams, with flexible remote work and a mission-focused environment serving national defense customers.

Qualifications

• Bachelor’s or master’s degree in computer science, engineering, security, or a related field.
• Proficiency in Python, with familiarity in other relevant languages (e.g., C++, C).
• Experience with Linux OS.
• Experience in AI/ML model development, testing, or deployment.
• U.S. citizenship required.

Responsibilities

• Design, plan, and perform Red Team assessments of AI systems, including: AI/ML model risks (e.g., adversarial attacks, LLM prompt injection, data/model leakage)
• Use automated testing tools and develop tactics, techniques, and procedures to evaluate system security, robustness, compliance, and trustworthiness across the AI lifecycle
• Collaborate with AI/ML developers, data scientists, platform engineers, and cybersecurity teams to build robust and secure systems from the ground up
• Help define red teaming methodologies and best practices aligned with standards such as NIST AI RMF and MITRE ATLAS
• Stay current on emerging threats, adversarial techniques, and responsible AI principles

Skills

Python

C++

Linux

AI/ML

U.S. citizenship

Education

Bachelor’s or Master’s degree in computer science/engineering/security

Tools

TensorFlow

PyTorch

Scikit-Learn

Job description

Lockheed Martin is seeking an AI engineer with a strong background in AI/ML to join the AI Center. You will design and lead Red Team assessments of AI systems, exploring adversarial risks and governance, and work with developers, data scientists, platform engineers, and cybersecurity teams to build secure, trustworthy systems.

This role offers opportunities to lead projects and teams, with flexible remote work and a mission-focused environment serving national defense customers.