Remote · US only jobs

AI Red Team Researcher

Reality DefenderRemote · US onlyFull-time4+ years experiencePosted 26 days ago

$155k–$185k/yr listed by the employer

This job is closed.

The employer took it down yesterday, after 19 days open. Here are similar open jobs.

  • Checked: On the company's own careers siteAshby board
  • Checked: Pay listedJob posting
  • Checked: No reposts foundAshby board
  • Note: Last seen open 9 days agoLive check
  • Trust score 100 / 100 · Strong
See all 5 checksShow fewer
How we check

Similar open jobs

See more like this

What you’ll do

  • Continuously test detection models across audio, video, images, and text using emerging generative tools and adversarial techniques.
  • Create realistic attack simulations and maintain reusable red-team infrastructure, including test harnesses, attack catalogs, and adversarial datasets.
  • Document and prioritize failures, collaborate with AI scientists and engineers on fixes, and verify fixes through regression testing.
  • Track emerging generative AI tools, research, and threat tradecraft; identify likely threats and inform product roadmap priorities.

Summarised from the posting by AI and can be wrong. The full description is the source.

Requirements

Licenses and certifications

  • Relevant certifications, such as OSCP (preferred)

Experience

  • 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 and TTS, face swap, lip-sync, or diffusion-based image and video tools, in an offensive or research context
  • Background in media forensics, signal processing, speech/audio, or computer vision (preferred)
  • Traditional red team or penetration testing experience in cloud, APIs, or web (preferred)
  • Published research, conference talks, CVEs, or open-source contributions in adversarial ML, deepfakes, or AI security (preferred)

Skills

  • Strong Python skills and practical ML fluency (PyTorch or similar)
  • Working knowledge of adversarial ML techniques, including evasion, adversarial perturbations, compression and post-processing attacks, and data poisoning, and how to measure model robustness
  • Familiarity with AI security tooling such as Garak, PyRIT, or the Adversarial Robustness Toolbox (preferred)

Other requirements

  • Ability to turn technical findings into prioritized, actionable guidance for engineers and non-technical audiences
  • Ability to thrive with ambiguity and minimal supervision

Benefits

Health insurance
Healthcare plans with 100% premium coverage for employees and partial coverage available for dependents, FSA/HSA programs
Dental & vision
Dental and vision plans with 100% premium coverage for employees and their dependents
Retirement plan
401(k) program
Paid time off
20 days of PTO per year
Parental leave
12 weeks of parental leave
Equity
Equity compensation
Learning & tuition
Learning and Development budget
Wellness & mental health
Monthly wellness benefits
Flexible schedule
Remote Fridays for NYC HQ employees
Life & disability insurance
Short- and long-term disability and life insurance plans with 100% premium coverage for employees
Commuter benefits
Commuter benefits for NYC HQ employees
Meals
For NYC HQ employees: daily in-office lunch through UberEats
Other
Annual company-sponsored offsite, For NYC HQ employees: happy hours and other local events

Full job description

From Reality Defender’s careers site

WHO WE ARE.

Reality Defender is an award-winning AI company that develops models to help enterprises and governments tell what’s real from what’s AI-generated. Our multi-model platform detects AI-generated video, audio, and images in real time, and stays robust against new generative tools as they emerge.

The question our customers are asking is changing. It’s no longer only “is this a deepfake?” It’s “is this real, and is it who it claims to be?” Every day, organizations ask us:

  • “Is the voice on this call a real person?”
  • “Is that video of our CEO real?”
  • “Is everyone in this meeting who they say they are?”
Show full descriptionShow less

We answer those questions in real time, across video, audio, images, and text, so security teams can act before the damage is done.

Reality Defender is backed by world-class investors including DCVC, Illuminate Financial, Y Combinator, Booz Allen Hamilton, IBM, Accenture, Rackhouse, and Argon VC. We work with leading enterprises, financial institutions, and government agencies to make sure AI-generated media can’t be used to deceive.

Youtube: Reality Defender Wins RSA Most Innovative Startup https://www.youtube.com/watch?v=TKOZmwyNUNM

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.

Something wrong with this job? Report it