Red Team Engineer

Job Summary

Focused on breaking detection models, the full-time Red Team Engineer will conduct adversarial testing and build attack simulations while working remotely within the U.S. or from the NYC headquarters.

Key responsibilities

• Run continuous adversarial testing against detection models across various media types, reproducing new generative tools and techniques
• Build realistic attack simulations that reflect real-world bad actor operations and maintain red team infrastructure
• Track the generative AI landscape and prioritize findings to inform product roadmap and remediation efforts

Required qualifications

• 4+ years of experience in offensive security, adversarial ML, or AI red teaming
• Hands-on experience with synthetic media generation tools in an offensive or research context
• Strong Python skills and practical fluency in machine learning frameworks like PyTorch
• Working knowledge of adversarial ML techniques and model robustness measurement
• Background in media forensics, signal processing, or computer vision is a plus