AI Security Engineer

Preamble

  • Pittsburgh, Pennsylvania
  • 30+ days ago

    Highlights

    The ideal candidate has a strong background in AI and understanding of cybersecurity principles, has been published in leading academic conferences (NeurIPS, ICLR, Black Hat, DEFCON, etc.), and has experience working at a frontier AI lab. This individual will be responsible for researching, designing, and implementing cutting-edge security controls to protect AI models, data pipelines, and infrastructure from adversarial attacks, privacy vulnerabilities, and regulatory risks.

    Numbers & Facts

    LocationPittsburgh, Pennsylvania
    Websitehttps://preamble.com

    Description

    We are seeking an experienced AI Security Engineer to lead the development of next-generation cybersecurity solutions for advanced AI systems. This individual will be responsible for researching, designing, and implementing cutting-edge security controls to protect AI models, data pipelines, and infrastructure from adversarial attacks, privacy vulnerabilities, and regulatory risks. The ideal candidate has a strong background in AI and understanding of cybersecurity principles, has been published in leading academic conferences (NeurIPS, ICLR, Black Hat, DEFCON, etc.), and has experience working at a frontier AI lab.



    Requirements

    • Experience: 5+ years in AI/ML with a strong focus on cybersecurity.

    • Education: Bachelor’s or Master’s in Computer Science, Cybersecurity, AI/ML, or a related field. PhD preferred.

    • Technical Expertise:

      • Strong understanding of AI security challenges, including adversarial ML, LLM backdoor, (in)direct prompt injections, model poisoning, and data leakage.

      • Proficiency in cybersecurity frameworks (NIST, MITRE ATLAS, OWASP AI Top 10) and security tools.

      • Hands-on experience with AI frameworks (TensorFlow, PyTorch, OpenAI API, Hugging Face) and securing AI pipelines.

      • Expertise in cryptography, secure data handling, and privacy-preserving AI techniques (federated learning, differential privacy).

      • Proficiency in Python and security-related programming (e.g., secure coding, AI model evaluation).

      • Familiarity with AI agents, autonomous agents, large language models (LLMs), and multi-modal AI systems.

    • Preferred: Experience in compliance, regulatory, or risk frameworks for AI (e.g., OWASP, MITRE, GDPR, HIPAA, GLBA, NIST AI RMF). An interest in robotics would be preferred as well.

    • Publication & Research: Proven track record of research contributions in top AI/ML and cybersecurity conferences.

    • Industry Experience: Prior work at a leading AI research lab, security-focused AI startup, or a major tech company’s AI division.



    Benefits

    • Competitive salary and equity options.

    • 100% paid medical insurance coverage. 

    • Research and publication opportunities.

    • Opportunity to work on cutting-edge AI security challenges that expand beyond software systems. 

    • Flexible work environment with remote and in-office options.

    • Access to industry-leading AI security research and resources.

    • A dynamic, mission-driven team shaping the future of AI security.


    Similar Jobs

    See more jobs