Remote Red Team Engineer — Adversarial ML & Deepfakes

Reality Defender Inc.; New York (NY); Remote; USD 155,000 - 185,000; Full time

Benefits offered by this job

Healthcare plans

Dental & Vision

Disability & life

Equity compensation

PTO 20 days

Parental leave

Learning budget

Wellness benefits

Annual offsite

Job summary

Reality Defender in NYC is seeking a Red Team Researcher to break our deepfake detection models using voice cloning, face swaps, and other synthetic media techniques across audio, video, image, and text. You will build attack tooling, run continuous adversarial testing, and translate findings into actionable guidance for engineers, product, and customers to improve model robustness.

4+ years in offensive security or adversarial ML are required; strong Python skills and research experience are

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 image and video tools — in an offensive or research context, not just reading about it.
• Strong Python skills and practical ML fluency (PyTorch or similar): build attack tooling, automate testing pipelines, and reason about model failures.
• Working knowledge of adversarial ML techniques — evasion, perturbations, attacks, data poisoning — and how to measure model robustness.
• Clear communicator who can turn technical findings into prioritized guidance for engineers and non-technical audiences.
• Background in media forensics, signal processing, speech/audio, or computer vision is nice to have.
• Certifications (OSCP) or familiarity with AI security tooling (Garak, PyRIT, ART) are nice to have.
• Published research, conference talks, CVEs, or OSS contributions in adversarial ML, deepfakes, or AI security is nice to have.

Responsibilities

• Run continuous adversarial testing against detection models across audio, video, image, and text.
• Build realistic, end-to-end attack simulations mapping how bad actors would operate.
• Maintain repeatable red team infrastructure: test harnesses, attack catalogs, datasets.
• Close the loop on findings with reproducible steps and regression verification.
• Track the generative AI landscape and triage techniques likely to be weaponized next.
• Partner with Product to shape roadmap priorities based on red team findings.

Skills

Offensive security

Adversarial ML

Python

AI security tools

Communication

Media forensics

Red team

Certifications

Research publications

Education

Media forensics

Signal processing

Speech/Audio

Computer vision

Tools

Garak

PyRIT

ART

Job description

Reality Defender in NYC is seeking a Red Team Researcher to break our deepfake detection models using voice cloning, face swaps, and other synthetic media techniques across audio, video, image, and text. You will build attack tooling, run continuous adversarial testing, and translate findings into actionable guidance for engineers, product, and customers to improve model robustness.

4+ years in offensive security or adversarial ML are required; strong Python skills and research experience are