- Partner with engineering and product teams to define and implement security requirements for applications, APIs, microservices, and AI systems.
- Conduct penetration testing, secure code reviews, and threat modeling, including AI-specific threat models.
- Plan and execute AI red teaming for prompt injection, jailbreaks, data exfiltration, excessive agency, and output abuse.
- Design and implement AI defenses, including guardrails, filtering, gateway controls, least-privilege tool scopes, human-in-the-loop checkpoints, logging, and kill switches.
- Lead application vulnerability management and drive remediation of findings from SAST, DAST, SCA, and penetration tests.
- Advise engineering, SRE, and product teams on secure coding, security architecture, and remediation.
- Establish application security and secure AI development standards aligned with OWASP, NIST, ISO, and industry frameworks.
- Track emerging security threats, especially AI attacks, and improve security practices.
PythonSQLJava+1 more