Senior Security Engineer, Trail of Bits
Agentic AI
$100-200k
+ performance-based bonuses
More information about location
Security engineering firm
Be an early applicant
Security engineering firm
101-200 employees
Be an early applicant
$100-200k
+ performance-based bonuses
More information about location
101-200 employees
Company mission
To help secure the world's most targeted organizations and products.
Role
Who you are
- 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
- Prompt Injection Proficiency: Practical experience designing and executing prompt injection workflows against production LLM systems, agentic pipelines, and tool-use environments, including familiarity with emerging taxonomies and mitigation approaches
- Programming Proficiency: Strong knowledge of multiple programming languages such as Rust, Golang, Kotlin, Swift, Objective-C, JavaScript/TypeScript, Python, Ruby, C and/or C++ for both security analysis and tool development
- Hacker Mindset: A creative and adversarial mindset, with a passion for discovering novel attack vectors and understanding how systems work across many layers of abstraction
- Communication Skills: Ability to effectively communicate complex security concepts to diverse stakeholders and deliver clear, actionable recommendations
What the job involves
- Trail of Bits seeks a Senior Security Engineer specializing in Application Security for Agentic AI systems, within our growing Software Assurance team
- You will conduct comprehensive security assessments of large language model systems, examining software across the AI supply chain and application stack — such as LLM web applications, agentic coding tools, training data and inference pipelines, and guardrail mechanisms
- Additionally, this role will be responsible for development, and operationalization of prompt injection techniques, for use in end-to-end application security reviews
- You will identify and analyze novel attack vectors and vulnerabilities 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 experience and adversarial thinking to the latest agentic systems and buisness integrations
- In addition to performing technical assessments, you will contribute to threat modeling, adoption risk frameworks for generative AI tooling, and delivering specialized training to clients on Agentic AI security concepts, including prompt injection, ML-specific attacks, and data pipeline threats
- 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
Our take
As more and more commercial activities go online, companies are increasingly exposed to cybersecurity threats. This requires organizations to get serious about their digital security infrastructure. As a result, the business of cybersecurity auditing has boomed.
Trail of bits is one such auditing firm with a signature method: combining its top-quality research in the cybersecurity field with the approaches of a real-world hacker. Distinguishing itself even further, the company has engaged in a new strategy fit for a new market - blockchain. The cybersecurity firm is now one of the world’s most prominent blockchain code auditors.
It's an exploding niche for which Trail of Bits has also been able to create an entirely new business line. While also auditing on behalf of blockchain software businesses, it is also expanding a service of engaging the government & large financial institutions for work on evaluating the risks of blockchain software.
Trail of Bits is well positioned as a result. Even if, as some commentators predict, the bottom falls out of the blockchain industry, the firm has used the momentum to reinforce its position as a thought leader on cutting-edge technology, establishing important partnerships that will last regardless.
Kirsty
Company Specialist at Welcome to the Jungle
Insights
18% employee growth in 12 months
Company
Funding (last 2 of 5 rounds)
Aug 2023
$4m
SEED
Jan 2018
$0.2m
GRANT
Total funding: $5.4m
Company benefits
- Health Insurance with no-monthly-premiums
- Vision, Dental, Life & Disability Insurance
- Access to Kindbody for gynecology and fertility care
- Access to HealthAdvocate, Teledoc & OneMedical
- 401k with 5% company matching
- Competitive salaries
- Ongoing bonus opportunities
- ConnectYourCare Flex Spending Account (FSA)
- Commuter Benefits
- Fitness stipends
- Four weeks of PTO
- Fifteen company holidays
- 4 months paid parental leave
- End-of-year performance bonus
- Continuing education, public presentations and blog posts
- Recruiting & referrals
- Conferences & off-sites
- Company & team outings
- Virtual events
- Continuing education
- Training sessions & learning courses
- Internal research & development Projects
- Charitable donation matching
- Relocation assistance
- 1Password subscription
- Work from home stipend
- Remote work friendly
Company HQ
Midtown East, New York, NY
Leadership
Dan Guido
(Co-Founder & CEO)Previously a Senior Security Consultant at iSEC Partners. Also worked as Threat Intelligence Lead for the U.S. Federal Reserve System. Former NSA Analyst.
Share this job
View 6 more jobs at Trail of Bits