Adversarial AI Red Team Engineer (Remote)

Reality Defender Inc.; United States; Remote; USD 155,000 - 185,000; Full time

Benefits offered by this job

Healthcare plans

Dental and Vision plans

Disability and life insurance

FSA/HSA and 401k

Equity compensation

20 days PTO per year

12 weeks Parental Leave

Learning and Development budget

Monthly wellness benefits

Annual company offsite

HQ NYC in-office lunch and commuter/RS

Job summary

Reality Defender is seeking a Red Team Engineer to break our detection models using cutting-edge deepfake tools, in a full-time role based at our NYC headquarters or remote within the U.S. You will drive adversarial testing across audio, video, image, and text, and translate findings into actionable security improvements.

You will build attack simulations, maintain red team infrastructure, and work with AI and Product teams to prioritize remediation.

Qualifications

• 4+ years of experience in offensive security, adversarial ML, AI red teaming, or ML engineering with a strong adversarial focus.
• Hands-on experience generating synthetic media — voice cloning and TTS, face swap, lip-sync, diffusion-based tools — in an offensive or research context.
• Strong Python skills and practical ML fluency (PyTorch or similar).
• Working knowledge of adversarial ML techniques — evasion, perturbations, data poisoning — and how to measure model robustness.
• Clear communicator who can translate findings into actionable guidance for engineers and non-technical audiences.
• Nice to have: background in media forensics, signal processing, speech/audio, or computer vision.
• Nice to have: OSCP or similar certifications; familiarity with security tooling.

Responsibilities

• Run continuous adversarial testing against detection models across audio, video, image, and text.
• Build realistic attack simulations mirroring real attacker operations.
• Develop repeatable red team infrastructure and an evolving adversarial dataset.
• Prioritize findings and provide reproducible steps to engineers and AI scientists.
• Track the AI security landscape and triage techniques likely to be weaponized next.
• Collaborate with Product to shape roadmap priorities from red team findings.
• Support Sales and Security with credible threat research and briefings.
• Contribute to platform adversarial testing with APIs and integrations.

Skills

Offensive security

Adversarial ML

Python

ML engineering

Communication

Tools

Garak

PyRIT

Adversarial Robustness Toolbox

Job description

Reality Defender is seeking a Red Team Engineer to break our detection models using cutting-edge deepfake tools, in a full-time role based at our NYC headquarters or remote within the U.S. You will drive adversarial testing across audio, video, image, and text, and translate findings into actionable security improvements.

You will build attack simulations, maintain red team infrastructure, and work with AI and Product teams to prioritize remediation.