AI Red Team Researcher

Reality Defender; New York (NY); À distance; USD 155 000 - 185 000; Plein temps

Avantages offerts par ce poste

Healthcare plans

Dental & Vision

Disability & life

Equity compensation

PTO 20 days

Parental leave

Learning budget

Wellness benefits

Annual offsite

Résumé du poste

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.

Responsabilités

• 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.

Connaissances

Offensive security

Adversarial ML

Python

AI security tools

Communication

Media forensics

Red team

Certifications

Research publications

Formation

Media forensics

Signal processing

Speech/Audio

Computer vision

Outils

Garak

PyRIT

ART

Description du poste

Who we are.

Reality Defender is an award-winning cybersecurity company helping enterprises and governments detect deepfakes and AI-generated media. Utilizing a patented multi-model approach, Reality Defender is robust against the bleeding edge of generative platforms producing video, audio, imagery, and text media. Reality Defender's API-first deepfake detection platform empowers teams and developers alike to identify fraud, disinformation campaigns, and harmful deepfakes in real time.

Backed by world class investors including DCVC, Illuminate Financial, Y Combinator, Booz Allen Hamilton, IBM, Accenture, Rackhouse, and Argon VC, Reality Defender works with leading enterprise clients, financial institutions, and governments in order to ensure AI-generated media is not used for malicious purposes.

Youtube: Reality Defender Wins RSA Most Innovative Startup

The Red Team Role

Reality Defender's AI Red Team exists to break our own detection models before adversaries do. As a Red Team Researcher, you'll get your hands on the newest deepfake tools the moment they appear — voice clones, real-time face swaps, injection attacks, multimodal impersonations — use them the way real attackers would, and turn every failure you uncover into a measurable fix shipped alongside our AI and Data teams. This is a full-time role based at our NYC headquarters or remote within the U.S., reporting to VP of Product. Responsibilities include:

• Run continuous adversarial testing against our detection models across audio, video, image, and text, reproducing new generative tools and techniques as they're released and stress-testing them against production models.

• Build realistic, end-to-end attack simulations that mirror how bad actors actually operate — cloned voices in call centers, real-time synthetic video in onboarding flows and job interviews, virtual camera and media injection, and coordinated cross-channel impersonation.

• Build and maintain repeatable red team infrastructure: test harnesses, attack catalogs, and an evolving adversarial dataset that every model release is validated against.

• Close the loop on findings — prioritize them, hand them to AI scientists and engineers with clean reproduction steps, and verify fixes through regression testing so they stick.

• Track the generative AI landscape (open-source models, commercial tools, research papers, and threat actor tradecraft) and triage which techniques are most likely to be weaponized next.

• Partner with Product to shape roadmap priorities based on what red team findings reveal.

• Support Sales, Marketing, and Solutions Engineering with credible, publishable research and threat briefings for enterprise and government customers.

• Contribute to adversarial testing of the broader platform — APIs and integrations — in partnership with Security.

• Help define the ethical guidelines and safe-handling practices for synthetic media used in testing.

Who you are.

• 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): you can build attack tooling, automate testing pipelines, and reason about why a model fails, not just that it did.

• Working knowledge of adversarial ML techniques — evasion, adversarial perturbations, compression and post-processing attacks, data poisoning — and how to measure model robustness.

• Clear communicator who can turn technical findings into prioritized, actionable guidance for engineers and non-technical audiences alike, and who thrives with ambiguity and minimal supervision.

• Background in media forensics, signal processing, speech/audio, or computer vision. (nice to have)

• Traditional red team or penetration testing experience (cloud, APIs, web), relevant certifications (e.g., OSCP), or familiarity with AI security tooling such as Garak, PyRIT, or the Adversarial Robustness Toolbox. (nice to have)

• Published research, conference talks, CVEs, or open-source contributions in adversarial ML, deepfakes, or AI security. (nice to have)

Within 12 months, you'll…

• Be recognized internally as a go-to authority on how deepfakes are made and how they evade detection.

• Have built adversarial testing infrastructure that scales across every modality with minimal manual effort.

• Have red team insights directly shaping the product roadmap and how we talk about risk with customers and government partners.

• Be identifying and leading testing on the next generation of threats — such as AI agent callers and real-time multimodal impersonation — before they show up in production.

What we offer.

Reality Defender offers the following benefits to all our employees, regardless of location:

• 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/Long-term disability and life insurance plans with 100% premium coverage for employees

• FSA/HSA and 401k 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 from Reality Defender's HQ in NYC, we offer the following benefits:

• Daily in-office lunch through UberEats

• Commuter benefits

• Remote Fridays

• Happy Hours and other local events

Base salary range: $155,000 - 185,000 based on experience and location. Includes equity.