AI Security Researcher
Hybrid · San Francisco, California, United States or Singapore, Singapore
Job Summary
Conduct security research against AI-powered applications, agentic systems, browsers, and emerging technologies. Investigate prompt injection, tool abuse, agent manipulation, data leakage, and other AI-specific attack vectors. Develop proof-of-concepts, testing frameworks, and research tooling to assess AI security risks. Perform penetration testing, security assessments, and architecture reviews of AI-powered products. Produce clear technical documentation, vulnerability reports, and reproducible research artifacts. Collaborate with product and engineering teams to remediate findings and improve product security. Monitor developments in AI security, adversarial machine learning, and offensive security research. Contribute to open-source projects and security community initiatives.
Required Qualifications
- Hands-on experience in offensive security, penetration testing, vulnerability research, bug bounty programs, or red teaming
- Ability to identify and responsibly disclose security vulnerabilities
- Experience assessing AI systems, LLM applications, agentic frameworks, or related technologies
- Strong programming skills with ability to build tooling and automate testing workflows
- Familiarity with prompt injection, AI abuse scenarios, model security, and emerging AI attack techniques
- Strong problem-solving skills and ability to operate independently
- Excellent written communication skills and ability to document technical findings clearly
Apply with one swipe on Sorce. We auto-fill applications and apply on your behalf — no cover letters, no 40-minute forms.
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.