Responsibilities

Probe AI systems, infrastructure, and applications for weaknesses through red teaming and penetration testing.
Work directly with engineers to remediate vulnerabilities.
Develop detection and response capabilities for threats.
Analyze AI-specific risks like training pipelines, inference systems, model architectures, and supply chain threats.
Build automated security testing tools.
Contribute to security metrics and raise engineering team's security awareness.

Requirements

6+ years of professional security engineering experience.
Deep hands-on experience with offensive security: red teaming, penetration testing, or vulnerability research.
Experience assessing cloud infrastructure security, preferably AWS (EC2, ECS, RDS, S3, IAM).
Ability to develop custom tools and automation (Python, Go).
Experience analyzing and exploiting web application vulnerabilities.
Strong understanding of threat actor techniques, tactics, and procedures (TTPs).
Ability to translate technical findings into actionable recommendations.
Bachelor's degree in Computer Science, Cybersecurity, or equivalent.

Experience with AI/ML system security: training pipelines, inference systems, model architectures.
Familiarity with AI-specific attacks: prompt injection, model poisoning, data extraction.
Fintech or financial services security experience.
Experience building security metrics and reporting.
Startup experience.
Certifications: OSCP, OSCE, GXPN.

100% employer-covered medical insurance for employees (75% dependents), dental, vision.
401(k) retirement savings.
Paid time off + federal holidays.
Parental leave.
Meals and fitness stipend.
Equity and career growth opportunities.