Artificial intelligence
10 Google DeepMind security engineers
These ten current and former Google DeepMind security engineers hold or held security engineering or security research roles at the lab. A reader can learn what security engineering work at Google DeepMind involves from people who have done it.
Professionals to explore
01—10Alexey Kurakin
LinkedInExperience: Senior Staff Research Engineer · Google DeepMind
Senior Staff Research Engineer at Google DeepMind since 2025 and Staff Research Engineer there from 2023; their summary says they work on the security and privacy of machine learning and LLMs. Alexey Kurakin was Staff Research Engineer at Google (2019–2023), according to their profile.
Chongyang Shi
LinkedInExperience: Senior Staff Software Engineer, Security · Google DeepMind
Senior Staff Software Engineer, Security at Google DeepMind since 2026, and Software Engineer, Security there from 2022; a highlight describes them as tech lead of Gemini Security Modeling, a team of 10+ members of technical staff. Chongyang Shi was Security Engineer at OVO (2020–2021).
Elie Bursztein
LinkedInExperience: Cybersecurity Research & Technical Lead · Google DeepMind
Cybersecurity Research & Technical Lead at Google DeepMind since 2023, a role a highlight describes as security technical lead and cybersecurity research lead. Elie Bursztein was Research Director at Google (2021–2023) and Sr. Staff Research Scientist at Google (2018–2021), according to their profile.
Kexin Zhu
LinkedInExperience: Software Engineer · Google DeepMind
Software Engineer at Google DeepMind since 2026, a role a highlight ties to GDM Security & Privacy Research. Kexin Zhu was Software Engineer at Google (2023–2026) and Software Engineer at Stripe (2022–2023), according to their profile, and is based in Sunnyvale.
Laurent Simon
LinkedInExperience: Security · Google DeepMind
Listed in Security at Google DeepMind since 2025, with a highlight naming agent security among their experience and a PhD in computer security from the University of Cambridge. Laurent Simon worked in Security at YouTube (2024–2025) and at Google (2019–2024), according to their profile.
Luís Miranda
LinkedInExperience: Staff Software Engineer · Google DeepMind
Staff Software Engineer at Google DeepMind since 2026, a role a highlight ties to agentic security. Luís Miranda is also listed as Staff Software Engineer at Google since 2016, with a headline naming Google Cloud Platform security and privacy engineering, and is based in Zurich.
Michael Borohovski
LinkedInExperience: Security Lead, Agentic Red Team · Google DeepMind
Security Lead, Agentic Red Team at Google DeepMind since 2026; their summary says they run the Agentic Red Team, which adversarially evaluates frontier AI systems for prompt injection and capability misuse. Michael Borohovski was Founder & CEO of Kobo Foundry (2025–2026), according to their profile.
Raluca Ada Popa
LinkedInExperience: Senior Staff Research Scientist · Google DeepMind
Senior Staff Research Scientist at Google DeepMind since 2024, a role a highlight describes as leading the Frontier Security team. Raluca Ada Popa is also listed as an associate professor at UC Berkeley College of Engineering since 2015 and as co-founder of OPAQUE Systems and PreVeil.
Raz Regev
LinkedInExperience: Senior Software Engineer · Google DeepMind
Senior Software Engineer at Google DeepMind since 2024, a role a highlight ties to Gen AI agent security. Raz Regev was Senior Software Engineer at Google (2020–2024) and Software Engineer at Google (2017–2020), according to their profile, and is based in Switzerland.
Vijay B.
LinkedInExperience: Former Chief Information Security Officer and Head of Cybersecurity Research · Google DeepMind
Chief Information Security Officer and Head of Cybersecurity Research at Google DeepMind (2019–2025), according to their profile. Vijay B. was Chief Information Security Officer & Chief Information Officer at BlackHawk Network (2016–2019) and Managing Principal at Mandiant (2012–2016).
Choose the right perspective
Match the person's focus to your question, since agent security, red teaming, privacy of machine learning and security leadership are different kinds of work. Check their seniority and dates, since a security lead and an individual engineer see the work from different angles.
Questions to take into the conversation
- 01How does securing a frontier model or AI agent differ from securing a conventional software product?
- 02Which attack surfaces, such as prompt injection or data leakage, take the most engineering effort to defend?
- 03How do security engineers and model researchers decide which risks to test for first?
Reaching Google DeepMind security engineers
How can I contact one of these Google DeepMind security engineers?
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 1 company: Google DeepMind, based on profile data retrieved on October 15, 2026. Being listed here doesn't mean someone has agreed to take calls.
How much does it cost to reach Google DeepMind security engineers?
You choose the offer, starting at $5 per person. The offer is what the person receives, and Instant Expert's fee is added on top, so a $100 offer costs you $125. The fee is 20% of what you pay. 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 Google DeepMind security engineers 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; roles marked former had ended by then. Check the linked profiles for current details. Inclusion does not imply Instant Expert membership or availability.
Request a correction or removal