Machine Learning Security Researcher

Who We Are

Founded in 2012 by 3 expert hackers with no investment capital, Trail of Bits is the premier place for security experts to boldly advance security and address technology’s newest and most challenging risks. It has helped secure some of the world's most targeted organizations and devices. Our combination of novel research with practical solutions reduces the security risks that our clients face from emerging technologies. Our work helps drive the security industry and the public understanding of the technology underlying our world.

Cybersecurity preparedness is a moving target. Companies like ours are the tip of the spear in the fight against attackers. Our research-based and custom-engineering approach ensures that our client’s capabilities are at the forefront of what’s available. For companies and technologies that live and die by their security, a proactive, tailored approach is required to keep one step ahead of attackers.

Democratizing security information is essential. As part of our business, we provide ongoing informational support through blogs, whitepapers, newsletters, meetups, and open-source tools. The more the community understands security, the more they’ll understand why a company like ours is so unique and valuable.

Role

Trail of Bits seeks a Machine Learning Security Researcher within our growing AI Assurance team. This role involves conducting cutting-edge security research on machine learning systems deployed by the world's most sophisticated AI organizations. The position focuses on identifying novel attack vectors, failure modes, and security vulnerabilities in state-of-the-art ML systems—from training pipelines and model architectures to deployment infrastructure and inference systems.

You will work directly with leading AI labs and frontier model developers to ensure their systems are robust against emerging threats. This is a research role that requires deep AI/ML expertise, with no application security background necessary. The role involves contributing to the broader AI/ML security research community through tool development, threat modeling frameworks, and publications, while helping to define what secure AI development looks like at the frontier.

What You’ll Achieve

• ML Security Research: Conduct original security research on cutting-edge machine learning systems, identifying novel attack vectors including adversarial examples, model poisoning, data extraction attacks, and jailbreaks for large language models and other foundation models.
• Client Assurance: Work directly with top-tier AI organizations (frontier labs, leading AI companies) to assess the security posture of their most advanced ML systems, providing expertise that matches their internal research capabilities.
• AI/ML Security Tool Development: Design and build novel security testing frameworks, evaluation methodologies, and open-source tools specifically for AI/ML security research—including adversarial robustness testing, model extraction detection, and automated vulnerability discovery systems.
• Threat Intelligence & Modeling: Develop comprehensive threat models for emerging AI/ML deployment patterns, anticipate future attack vectors, and establish security frameworks that can scale with rapidly evolving AI capabilities.
• Research Community Engagement: Publish findings, present at security and AI/ML conferences, and contribute to the broader AI/ML security research discourse through papers, blog posts, and open-source contributions.
• Cross-Disciplinary Collaboration: Bridge AI/ML research and security engineering, translating complex adversarial AI/ML concepts to diverse stakeholders and working closely with Trail of Bits' broader security research teams.
  

What You’ll Bring

• Advanced AI/ML Research Background: PhD-level expertise (completed, near completion, or equivalent research experience) in machine learning, deep learning, or related fields with demonstrated research contributions.
  
• AI/ML Security Knowledge: Strong understanding of adversarial machine learning, including familiarity with attack paradigms such as evasion attacks, poisoning attacks, model inversion, membership inference, backdoor attacks, or prompt injection/jailbreaking techniques. Experience specifically in adversarial ML, robustness, or AI safety research is highly valued.
  
• Deep Technical ML Expertise: Extensive hands-on experience with modern ML frameworks (PyTorch, JAX, TensorFlow), transformer architectures, training methodologies, and the full ML development lifecycle from data pipelines to deployment. Familiarity with CUDA programming, GPU optimization, or ML systems performance is a plus.