Senior Offensive AI Security Researcher
Salary not listed • Israel - Tel Aviv • Full-time
Posted 13d ago
About the job
Salesforce is seeking a Senior Offensive AI Security Researcher to lead novel adversarial research across its AI ecosystem. This role focuses on uncovering critical and systemic vulnerabilities before they can be exploited, going beyond individual bug finding to scope, design, and execute advanced research into emerging AI threat vectors. The researcher will combine academic insights with practical offensive methodologies to establish new TTPs targeting complex AI paradigms, including prompt injection, tool abuse, RAG system poisoning, data extraction, and model/data supply chain compromises. You will act as a trusted partner to engineering and architecture teams, providing an offensive security perspective to shape threat models, guide AI architecture decisions, support corporate governance, and contribute to Salesforce’s Generative AI Security Standard.
Responsibilities
- Lead novel AI security research, scoping, designing, and executing advanced adversarial research across Salesforce’s AI ecosystem with a risk-based approach.
- Innovate and operationalize AI attack techniques by combining academic research with practical offensive methodologies to establish new TTPs targeting complex AI paradigms.
- Guide AI strategy and security standards by providing an offensive security perspective to shape AI architecture, internal threat models, and corporate governance.
- Disseminate research findings through internal and external threat intelligence, vulnerability analyses, and security research publications.
Requirements
- 5+ years of experience in offensive security roles (vulnerability research, penetration testing, application security, or security engineering).
- 2+ years of hands-on experience auditing, breaking, or researching ML/AI systems, with deep expertise in LLM attack surfaces and frameworks.
- Deep technical understanding of modern AI design patterns, including RAG, autonomous agentic workflows, model context protocols, and AI pipelines.
- High proficiency in Python for exploit proof-of-concept development, data analysis, and technical evaluation.
- Proven track record of leading complex security initiatives and communicating technical risks to both research engineers and executive leadership.