Red Team Engineer

Reality Defender•New York, NY

1d•$155,000 - $185,000

About The Position

Reality Defender is an award-winning cybersecurity company that helps enterprises and governments detect deepfakes and AI-generated media. Its API-first platform uses a patented multi-model approach to detect video, audio, imagery, and text in real time. The Red Team Engineer joins the AI Red Team, which tests the company’s detection models against emerging generative tools and attacker techniques, turns discovered weaknesses into measurable fixes, and works alongside AI, Data, Product, and Security teams. This is a full-time role based at the company’s New York City headquarters or remotely within the United States, reporting to the VP of Product. The role involves continuous adversarial testing across audio, video, image, and text; realistic end-to-end attack simulations; development of repeatable test infrastructure and adversarial datasets; and regression testing to verify that fixes work. The engineer will monitor generative AI tools, research, and threat actor techniques, help shape product priorities, support customer-facing research and briefings, test platform APIs and integrations with Security, and contribute to ethical guidelines for synthetic media testing. In the first month, the engineer will learn the detection architecture and red team program, meet key counterparts, test recently released generative techniques against production models, and deliver a prioritized findings report. By three months, they are expected to own an attack area, expand testing tools and automation, drive a finding through remediation, and establish a threat-update cadence. By six months, they will make red team testing a standard part of model releases for their area, build realistic multimodal simulations, track robustness improvements, and contribute to an external publication or customer-facing asset. By twelve months, they will help scale adversarial testing across modalities, inform product and customer risk priorities, and lead testing on emerging threats.

Requirements

At least 4 years of experience in offensive security, adversarial machine learning, AI red teaming, or machine learning engineering with a strong adversarial focus.
Hands-on experience generating synthetic media, such as voice clones and text-to-speech, face swaps, lip-sync, or diffusion-based image and video, in an offensive or research context.
Strong Python skills and practical machine learning fluency, such as PyTorch or similar, including the ability to build attack tooling, automate testing pipelines, and reason about model failures.
Working knowledge of adversarial machine learning techniques, including evasion, adversarial perturbations, compression and post-processing attacks, and data poisoning, and how to measure model robustness.
Clear communication skills, including the ability to turn technical findings into prioritized, actionable guidance for technical and non-technical audiences.
Ability to work with ambiguity and minimal supervision.

Nice To Haves

Background in media forensics, signal processing, speech/audio, or computer vision.
Traditional red team or penetration testing experience in cloud, APIs, or web security.
Relevant certifications, such as OSCP.
Familiarity with AI security tools such as Garak, PyRIT, or the Adversarial Robustness Toolbox.
Published research, conference talks, CVEs, or open-source contributions in adversarial machine learning, deepfakes, or AI security.

Responsibilities

Run continuous adversarial testing against detection models across audio, video, image, and text, reproducing new generative tools and stress-testing production models.
Build realistic, end-to-end attack simulations that reflect how bad actors operate, including voice cloning, synthetic video, virtual camera and media injection, and cross-channel impersonation.
Build and maintain red team infrastructure, including test harnesses, attack catalogs, and an evolving adversarial dataset used to validate model releases.
Prioritize findings, provide AI scientists and engineers with clear reproduction steps, and verify fixes through regression testing.
Track generative AI tools, research, and threat actor tradecraft, and assess which techniques are most likely to be weaponized.
Partner with Product to inform roadmap priorities based on red team findings.
Support Sales, Marketing, and Solutions Engineering with publishable research and threat briefings for enterprise and government customers.
Contribute to adversarial testing of platform APIs and integrations in partnership with Security.
Help define ethical guidelines and safe-handling practices for synthetic media used in testing.
Own a defined attack area, expand attack catalogs and test automation, and establish a cadence for sharing threat landscape updates.
Help integrate red team testing into model releases, measure robustness improvements, and contribute to external publications or customer-facing materials.

Benefits

Healthcare plans with 100% premium coverage for employees and partial coverage available for dependents.
Dental and vision plans with 100% premium coverage for employees and their dependents.
Short- and long-term disability and life insurance plans with 100% premium coverage for employees.
FSA/HSA programs.
401(k) programs.
Equity compensation.
20 days of PTO per year.
12 weeks of parental leave.
Learning and development budget.
Monthly wellness benefits.
Annual company-sponsored offsite.
For employees working at the NYC headquarters: daily in-office lunch through UberEats, commuter benefits, remote Fridays, happy hours, and other local events.