Description

Key Responsibilities

The selected resources will provide immediate execution capacity across ERD reviews, Threat Modeling, and third-party AI Agent security testing. Core responsibilities include:

1. Conduct security and privacy design reviews of services, applications, APIs, engineering proposals, and AI integrations; evaluate architecture, data flows, access controls, trust boundaries, and proposed safeguards.
2. Perform threat modeling for critical services and AI agents, identifying attack surfaces, threat scenarios, potential attack paths, mitigations, and residual risk.
3. Assess third-party AI agents through hands-on adversarial security testing, including prompt injection, tool misuse, data access, permissions, external integrations, excessive agency, and sensitive-data exposure.
4. Document actionable findings, risk assessments, supporting evidence, and practical remediation guidance; partner with engineering and security teams through remediation and validation.
5. Support repeatable security assessment processes, including review checklists, threat models, test cases, reporting templates, and AI-assisted/automation workflows where appropriate.

Minimum Qualifications

• 8+ years of professional experience in security engineering, application security, product security, offensive security, systems architecture, or a related technical security field.
• Demonstrated experience reviewing complex technical designs and identifying security risks in applications, APIs, cloud services, microservices, or distributed systems.
• Strong knowledge of threat modeling, vulnerability classification, risk modeling, authentication/authorization, least privilege, and data protection principles.
• Hands-on experience with security testing, vulnerability investigation, penetration/adversarial testing, or validating security controls.
• Ability to communicate technical findings clearly and collaborate directly with engineering, security, privacy, and third-party stakeholders.
• Preferred qualifications include experience assessing AI/LLM agents, prompt injection and unsafe tool use, privacy design reviews, cloud environments, and security automation using Python, Go, Bash, or similar languages.

Good to Have

• Demonstrated hands-on penetration testing and vulnerability assessment experience across applications, APIs, cloud infrastructure, and networks, including identifying and validating real-world attack paths and providing actionable remediation guidance

Key Skills

Education

Bachelor's degree