Senior Security Engineer, AI/ML

Salary: $10,000 Location Type: Remote Employment Type: [Not specified]

Position Overview

Trail of Bits seeks a Senior Security Engineer, AI/ML to join our growing Software Assurance team. This role involves conducting comprehensive security assessments of machine learning (ML) and large language model (LLM) systems. You will examine software across the AI/ML supply chain and stack, including LLM web applications, training data pipelines, neural network architectures, AI/ML frameworks, and CUDA-based libraries. The position focuses on identifying and analyzing novel attack vectors and vulnerabilities specific to MLops environments, with an emphasis on potential failure modes, vectors for model performance degradation, and unauthorized access to sensitive data and model parameters. In addition to technical assessments, you will contribute to threat modeling, evaluate AI adoption risk frameworks, and deliver specialized training to clients on AI security concepts, including AI/ML-specific attacks, AI safety, and pipeline threats.

Responsibilities

AI/ML Security Assessment

• Conduct comprehensive security assessments of AI/ML pipelines, tools, and frameworks.
• Examine vulnerabilities in model architectures, training processes, and deployment infrastructure.
• Develop mitigation strategies for identified vulnerabilities.

AI/ML Security Controls

• Design and develop security frameworks and tools specifically for AI/ML systems.
• Implement model robustness testing, data poisoning detection, and protection against adversarial attacks.

Application Security Assessment

• Conduct security assessments of client code bases using static analysis, dynamic testing, and manual code review.
• Identify vulnerabilities and develop mitigation strategies, with a focus on findings at the intersection of application security and AI/ML security.

AI/ML Threat Modeling

• Conduct threat modeling and risk assessments to proactively identify potential risks for clients.
• Develop mitigation strategies for future prevention.

Client Engagement

• Work with leading industry teams to review system code and architecture.
• Help assure client products through system analysis and modeling.

AI Policy & Compliance Initiatives

• Develop and contribute to AI/ML regulatory frameworks.
• Establish assurance methods and auditing processes for mission-critical AI applications.
• Ensure alignment with emerging industry standards and safety requirements.

Requirements

AI/ML Security Expertise

• Extensive experience in AI/ML security.
• Demonstrated ability to identify and mitigate ML-specific vulnerabilities across complex systems.

Technical AI/ML Knowledge

• Deep understanding of AI/ML architectures and frameworks (e.g., PyTorch, Jax, LangChain, RAG systems).

About Trail of Bits

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. We have 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.

Application Instructions

[Not specified]