Artificial intelligence
10 AI red teaming experts
These ten professionals have worked on AI red teams, adversarially testing AI models, generative AI applications and AI agents. A reader can learn how AI red teaming experts approach their work from people who have done it.
Professionals to explore
01—10Aviad Klein
LinkedInExperience: GenAI Security Researcher LLM Red Teaming · Alice (Formerly ActiveFence)
GenAI Security Researcher LLM Red Teaming at Alice (formerly ActiveFence) since 2024; the profile says he specializes in black-box red teaming of production-grade models from leading companies to find failure modes. Earlier roles at the company were Reverse Engineer (2023–2024) and Malware Researcher (2022–2023).
Daniel Fabian
LinkedInExperience: Manager AI Red Team, uber-TL for Red Teaming at Google · Google
Manager AI Red Team, uber-TL for Red Teaming at Google since 2023; the profile describes managing the AI and privacy red teams. He was Manager, Security Privacy ML Red Teams at Google (2019–2023) and Tech Lead Offensive Security at Google (2015–2019).
Jacob Johnson, M.A.
LinkedInExperience: Senior Red Team Operations Lead · LinkedIn
Senior Red Team Operations Lead at LinkedIn since 2026; the profile says he leads LinkedIn's red team operations across AI safety and misuse testing and is building red team operations from the ground up. He is also Senior Red Team Operations Manager at Innodata Inc. since 2025 and earlier held AI red team roles at Scale AI (2024–2025).
Jason Ross
LinkedInExperience: Product Security Principal (AI Red Team/ExploitAI) · Salesforce
Product Security Principal (AI Red Team/ExploitAI) at Salesforce since 2024; the profile says he performs adversarial testing and defense of deployed generative AI applications, agentic systems and the LLMs powering them, with a focus on prompt injection. Earlier he was Lead/Senior Enterprise Security Engineer at Salesforce (2021–2024) and Principal / Senior Consultant at NCC Group (2015–2021).
Joseph Lucas
LinkedInExperience: Principal Security Engineer, AI Red Team (Offensive Security) · NVIDIA
Principal Security Engineer, AI Red Team (Offensive Security) at NVIDIA (2022–2026), where the profile says he built an AI Red Team to improve security across the full machine learning life cycle and led dozens of security assessments; Senior Manager, AI Red Team at NVIDIA since 2026. Earlier he was Senior TPM, Red Team at Amazon Web Services (AWS) (2021–2022).
Michael Borohovski
LinkedInExperience: Security Lead, Agentic Red Team · Google DeepMind
Security Lead, Agentic Red Team at Google DeepMind since 2026; the profile says he runs the Agentic Red Team, which adversarially evaluates frontier AI systems for prompt injection, capability misuse and new attack surfaces. He was Founder & CEO of Kobo Foundry (2025–2026), and the headline names him a former founder and CTO of Tinfoil Security.
Nikhil Sanil
LinkedInExperience: Security Engineer · Amazon
Security Engineer at Amazon since 2025, after a Security Engineer role at Amazon Web Services (AWS) in 2025; the profile describes building adversarial testing and evaluation infrastructure and red teaming Amazon's models to find new AI risks before production. Earlier he was VP; Information Security at Bank of America (2016–2025).
Pete Bryan
LinkedInExperience: Technical Lead - AI Red Team · Microsoft
Technical Lead - AI Red Team at Microsoft since 2023; the profile says he helps lead Microsoft's AI Red Team, working to make the AI systems Microsoft develops safe and secure. Earlier Microsoft roles include Principal Security Research Manager (2022–2023) and Senior Security Researcher (2019–2022).
Richard Lundeen
LinkedInExperience: Principal Software Engineering Lead - AI Red Team · Microsoft
Principal Software Engineering Lead - AI Red Team at Microsoft since 2023; the profile says he leads a group of red teamers, ML researchers and developers building software that emulates real-world attacks and finds failures in Microsoft's AI systems, including the open source PyRIT repository. Earlier he was Senior Security Lead - Windows Platform Red Team at Microsoft (2013–2015).
Victoria (Tori) Westerhoff
LinkedInExperience: Principal AI Security Researcher, Leading Microsoft AI Red Team Ops · Microsoft
Principal AI Security Researcher, Leading Microsoft AI Red Team Ops at Microsoft since 2023; the profile describes leading all AI security and safety red team operations and frontier testing. Earlier Microsoft roles include Senior Manager, Strategy and Business Planner for Mixed Reality (2021–2023) and People Analytics Lead (2018–2021).
Choose the right perspective
Match the person's focus to your system, since red teaming a frontier model, a deployed generative AI application and an agentic system call for different attacks. Prefer someone who has led or built a red team if your question is about staffing and process rather than specific attack techniques.
Questions to take into the conversation
- 01How do you decide what to test first when red teaming a new AI model or AI feature?
- 02How do you turn red team findings into fixes that product and model teams will actually ship?
- 03Which parts of AI red teaming can be automated with tools, and which still need people?
Reaching AI red teaming experts
How can I contact one of these AI red teaming experts?
Pick one of the 10 people on this page and choose "Book a paid call", or describe your project to find others. You offer a fee for a 15-minute call or a written answer, Instant Expert finds the person's work email and sends the invitation, and they decide whether to accept. The list covers 8 companies, including Alice (Formerly ActiveFence), Google and LinkedIn, based on profile data retrieved on October 9, 2026. Being listed here doesn't mean someone has agreed to take calls.
How much does it cost to reach AI red teaming experts?
You choose the offer, starting at $5 per person. It includes Instant Expert's 20% fee, so an offer that pays the person $100 costs you $125. You're charged only when the person books the call or sends the answer.
What if they don't reply?
You pay nothing. Instant Expert sends follow-up reminders, and if the person hasn't booked or answered within 7 days, the request expires and any hold on your card is released. You can invite several of the 10 people on this list at once and cap your total spend, so you pay only for the ones who accept.
Can an AI agent ask one of these AI red teaming experts a question?
Yes. An agent with a USDC wallet on Base can ask one question without an Instant Expert account. It names the person, for example by the LinkedIn URL on this page, and pays per ask over x402 (HTTP 402). The person answers in writing or by voice note, and if nobody answers within 7 days, the payment goes back to the wallet automatically. x402 docs
About this directory
This is a professional research starting point based on business profile data retrieved on . Titles and companies reflect that source snapshot and may describe past or present roles. Check the linked profiles for current details. Inclusion does not imply Instant Expert membership or availability.
Request a correction or removal