Senior Security Engineer, Agentic AI

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 Senior Security Engineer specializing in Agentic AI Security for our Software Assurance team. You will discover and exploit novel vulnerabilities in agentic AI systems — finding the breaks before your clients do. You'll develop sophisticated prompt injection attacks, test agent orchestration weaknesses, and identify real-world failure modes in LLM tool use, training data pipelines, and guardrail mechanisms. You will identify and analyze novel attack vectors specific to AI and agentic environments, focusing on real-world failure modes, system integration issues, and unauthorized access vectors. This role allows you to apply application security expertise and adversarial thinking to the latest agentic systems and business integrations.

In addition to performing technical assessments, you will develop threat models for agentic AI systems, contribute to risk frameworks for generative AI deployment, and deliver specialized training to clients on novel exploitation techniques in agentic AI security.

What You'll Achieve

• Agentic AI Security Assessments - Conduct comprehensive application security assessments of agentic AI pipelines, tools, and frameworks for leading companies and labs. Examine vulnerabilities in model architectures, guardrails, and deployment infrastructure while developing mitigation strategies.
• Prompt Injection Research & Development - Develop and share novel prompt injection techniques targeting agentic workflows, including indirect injection via tool outputs, multi-turn manipulation, and cross-agent exploitation. Produce actionable attack libraries and defensive countermeasures for client engagements.
• Application Security Assessment - Conduct security assessments of client code bases using a combination of static analysis, dynamic testing, and manual code review, identifying vulnerabilities and developing mitigation strategies, with a focus on findings at the intersection of application security and Agentic AI security.
• Threat Modeling - Conduct threat modeling and risk assessments to proactively identify potential risks for clients and develop mitigation strategies for future prevention, with particular attention to prompt injection attack surfaces in agentic orchestration layers.
• Client Engagement - Work with leading industry teams to review system code and architecture, and help assure their products through system analysis and modeling.
• AI Policy & Compliance Initiatives - Develop and contribute to AI regulatory frameworks, establishing assurance methods and auditing processes for mission-critical AI applications while ensuring alignment with emerging industry standards and safety requirements.

What You'll Bring

• AI Security Expertise - Demonstrated interest and experience in agentic AI security, with demonstrated ability to identify and mitigate AI-specific vulnerabilities across complex systems, including hands-on experience with prompt injection attacks and defenses.
• Technical AI Knowledge -  Deep understanding of AI/ML architectures, frameworks (PyTorch, JAX, LangChain, RAG systems, etc.), and MLOps practices, combined with robust security engineering expertise.
• Application Security Skills - Track record of conducting technical security assessments of software, including software and system hardening, security policy analysis, and implementing effective security measures.
• P