Description

Own AI and ML security strategies, threat modeling, and red teaming programs to ensure adversarial resilience.

This role is on-site.

Responsibilities

• Develop secure AI architectures and review code to ensure adversarial resilience.
• Conduct discovery, threat modeling, and adversarial testing on generative AI and RAG pipelines.
• Define and implement AI red teaming methodologies, playbooks, and success metrics.
• Reduce vulnerabilities by adhering to industry standards and emerging AI safety research.
• Collaborate with product, data science, and risk stakeholders to align on risk tolerance.

Required Skills

• 5+ years applied security engineering experience.
• Proficiency in Threat Modeling, Penetration Testing, and Python.
• Experience with Infrastructure as Code: Terraform, CloudFormation.
• Knowledge of MITRE ATLAS and OWASP frameworks.
• Understanding of AI/ML systems and security concepts.

Preferred Skills

• Expertise in AI red teaming exercises using tools like PyRIT and Garak.
• Experience with custom LLM evaluation harnesses and enterprise generative AI security.
• Contributions to AI security or open-source security projects.

Key Skills

Education

Any Graduate