Security Researcher
Core
Research end-to-end security of AI systems, including agents, frameworks, runtimes, and infrastructure, by finding vulnerabilities and building full working exploits.
Role type
Senior Security Researcher (AI Security)
Builds
Full exploit chains and proof-of-concept vulnerabilities for AI systems
Domain
Artificial Intelligence / Cybersecurity
Deliverable
production ML models
Required skills
Vulnerability research, reverse engineering, exploit development, code analysis, understanding of modern software frameworks, memory corruption, unsafe deserialization, logic flaws
Preferred skills
AI system research, agent framework experience, published research (CVEs, talks, blogs)
Technologies
IDA Pro, Ghidra
Responsibilities
Research security of AI agents and frameworks, reverse engineer complex software without source code, develop working exploits from identified vulnerabilities, analyze defenses and bypass them, share findings via coordinated disclosure and conference talks
Seniority
Senior, hands-on IC