Lead design and execution of red team exercises vs generative AI.
Track AI security, adversarial ML, and responsible AI to strengthen guardrails.
Build production-grade red-teaming tools, test cases, and evaluation procedures.
Define KPIs and report findings with remediation guidance.
Own the technical vision and end-to-end development of red-teaming tools.

🎯 Requirements

B.S. in Computer Science, Engineering, or equivalent.
Strong Python skills; production-grade software; experience with LLMs.
Led technical projects end-to-end, owning architecture and delivery.
Knowledge of cybersecurity/AI security: prompt injection, adversarial ML.
Hands-on adversarial ML/AI experience.
Understanding ML/AI concepts: architectures, training, eval, LLMs.
Experience shaping product direction or roadmap (preferred).

🎁 Benefits

Various health plans.
Time off for vacation and sick time.
Parental leave options.
Retirement options.
Education reimbursement.
In-office perks and more.

Apply on employer's website

This employer gathers applications via their own applicant tracking system.

You will be redirected to an external application form.

Share job

Meet JobCopilot: Your Personal AI Job Hunter

Automatically Apply to Engineering Jobs. Just set your preferences and Job Copilot will do the rest — finding, filtering, and applying while you focus on what matters.

Activate JobCopilot