Senior Offensive AI Security Researcher
Core
Lead novel adversarial research across Salesforce's AI ecosystem to uncover critical vulnerabilities in emerging AI threat vectors before exploitation.
Role type
Senior IC offensive AI security researcher
Builds
Internal threat models, AI architecture decisions, and Salesforce's Generative AI Security Standard
Domain
Generative AI security, LLM attack surfaces, agentic workflows
Deliverable
production ML models
Required skills
Offensive security research, LLM attack surface auditing, RAG system security, Python exploit development, risk-based threat modeling
Preferred skills
Advanced degree in CS/ML/Cybersecurity, public offensive security research portfolio, auditing modern AI development ecosystems
Technologies
OWASP Top 10 for LLMs, MITRE ATLAS, PyTorch, Hugging Face, LangChain, vector databases
Responsibilities
Scope and execute advanced adversarial research on indirect prompt injection, tool abuse, RAG poisoning, and data extraction; establish new TTPs for complex AI paradigms; guide AI architecture and corporate governance; publish threat intelligence and vulnerability analyses
Seniority
Senior, hands-on IC
