AI Red Team Researcher

Job Description: - Run continuous adversarial testing against detection models across audio, video, image, and text

• Reproduce new generative tools and techniques and stress-test them against production models
• Build realistic, end-to-end attack simulations mirroring real bad-actor operations
• Build and maintain red team infrastructure, including test harnesses, attack catalogs, and adversarial datasets
• Prioritize findings and provide AI scientists and engineers with clear reproduction steps
• Verify fixes through regression testing
• Track generative AI tools, research, and threat actor tradecraft and triage likely weaponized techniques
• Partner with Product to shape roadmap priorities
• Support Sales, Marketing, and Solutions Engineering with publishable research and threat briefings
• Contribute to adversarial testing of APIs and integrations with Security
• Help define ethical guidelines and safe-handling practices for synthetic media
• Report to the VP of Product
• Within 12 months, become an internal authority on deepfake creation and evasion, scale adversarial testing infrastructure, shape product and customer risk discussions, and lead testing of emerging threats

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 and TTS, face swap, lip-sync, and diffusion-based image and video tools, in an offensive or research context
• Strong Python skills
• Practical ML fluency with PyTorch or similar
• Ability to build attack tooling, automate testing pipelines, and reason about model failures
• Working knowledge of adversarial ML techniques, including evasion, adversarial perturbations, compression and post-processing attacks, and data poisoning
• Ability to measure model robustness
• Ability to communicate technical findings as prioritized, actionable guidance for technical and non-technical audiences
• Background in media forensics, signal processing, speech/audio, or computer vision (nice to have)
• Traditional red team or penetration testing experience, relevant certifications such as OSCP, or familiarity with 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)
• Authorization to work in the U.S. is requested in the application
• Must be willing to relocate if not currently located in or near NYC for the headquarters-based option

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/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
• Daily in-office lunch through UberEats for HQ employees
• Commuter benefits for HQ employees
• Remote Fridays for HQ employees
• Happy Hours and other local events for HQ employees
• Eligibility for annual performance bonus