Red Team Engineer
Reality Defender3 hours ago
Base Salary
$155k - $185k/yr
Responsibilities
- Run continuous adversarial testing against audio, video, image, and text detection models.
- Build realistic end-to-end attack simulations involving voice cloning, synthetic video, media injection, and cross-channel impersonation.
- Build and maintain red-team infrastructure, including test harnesses, attack catalogs, and adversarial datasets.
- Prioritize findings, provide reproducible guidance to AI scientists and engineers, and verify fixes through regression testing.
- Track emerging generative AI tools, research, and threat-actor tradecraft and assess likely weaponization.
- Partner with Product, Security, Sales, Marketing, and Solutions Engineering on roadmap priorities, threat briefings, and platform testing.
- Help define ethical guidelines and safe-handling practices for synthetic media testing.
Requirements
- 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, including voice cloning, text-to-speech, face swapping, lip-sync, and diffusion-based image or video tools.
- Strong Python skills and practical ML fluency, including PyTorch or similar tools.
- Working knowledge of evasion, adversarial perturbations, compression and post-processing attacks, data poisoning, and model-robustness measurement.
- Ability to communicate technical findings as prioritized, actionable guidance for technical and non-technical audiences.
- Preferred background in media forensics, signal processing, speech/audio, or computer vision.
- Preferred traditional red-team or penetration-testing experience, relevant certifications such as OSCP, or familiarity with Garak, PyRIT, or the Adversarial Robustness Toolbox.
- Published research, conference talks, CVEs, or open-source contributions in adversarial ML, deepfakes, or AI security are preferred.
Benefits
- Healthcare plans with 100% employee premium coverage and partial dependent coverage.
- Dental and vision plans with 100% premium coverage for employees and dependents.
- Short- and long-term disability and life insurance with 100% employee premium coverage.
- FSA/HSA and 401k programs, equity compensation, 20 days of PTO, 12 weeks of parental leave, learning and development budget, monthly wellness benefits, and an annual company-sponsored offsite.
- Full-time role based at the NYC headquarters or remote within the U.S.
- NYC employees receive daily in-office lunch through UberEats, commuter benefits, remote Fridays, and local events.
About Reality Defender
Reality Defender builds AI models and an API-first platform to detect deepfakes across audio, video, images, and text for enterprises and governments. It offers an API and enterprise software to embed detection into call centers, identity verification, fraud prevention, and media workflows. Founded in 2021 and headquartered in New York, the privately held company is backed by investors including DCVC and Y Combinator.