P
AI Security Researcher
Not specifiedFull-timeSecurity ResearchCybersecurity
Conduct engineering-level application security work and research offensive techniques targeting AI/ML systems. Partner with development teams and enterprise customers on assessments, red-team engagements, and practical security recommendations.
Responsibilities
- Review software architectures and code, and work with development teams throughout the development lifecycle
- Lead AI security assessments and red-team engagements for enterprise customers
- Identify vulnerabilities in AI/ML systems, agentic workflows, and LLM-based applications
- Enhance application security processes with agentic tools and AI security layers
- Research attack techniques including prompt injection, model manipulation, and agentic framework exploits
- Translate offensive findings into actionable recommendations for customers and internal teams
- Research emerging AI attack surfaces and contribute to AI threat knowledge
Requirements
- Hands-on application security experience, including code and architecture reviews alongside development teams
- At least one year of dedicated AI security research, experimentation, or offensive engagement experience
- Offensive security skills focused on AI-specific attack vectors
- Strong understanding of AI/ML, LLMs, agentic systems, and common AI application architectures
- Able to read and write code, build tools, and understand codebases
- Strong communication skills and comfort working directly with enterprise customers
- Fluent English
Nice to have
- Published research or public presentations on AI security
- Traditional penetration testing or red-team experience
- Experience building or deploying AI/ML systems