Research Scientist Tech Lead (AI Security)

TL;DR

Research Scientist Tech Lead (AI Security): Leading research and development in contextual security and prompt injection resilience for generative AI models, focusing on improving privacy and security in Gemini and related products. Focus on managing a research team, driving impactful AI security projects, and integrating solutions into production and open source.

Location: Must be based in Mountain View, New York City, or San Francisco, United States

Salary: $248,000 - $349,000 USD per year

Company

hirify.global is a leading AI research company advancing artificial intelligence for public benefit, focusing on safety and ethics in AI development.

What you will do

• Lead and grow a team of researchers focused on contextual security and prompt injection challenges.
• Drive fundamental research and develop solutions for key AI security products.
• Identify impactful privacy and security problems in generative models through auto-red teaming.
• Build and test post-training data and tools to improve model security capabilities.
• Generalize solutions into reusable libraries and frameworks for broader application across Google.
• Share knowledge through publications, open source contributions, and education.

Requirements

• Must be based in the United States (Mountain View, New York City, or San Francisco).
• PhD in Computer Science or related field, or 5+ years relevant experience.
• Experience leading complex AI security, privacy, or safety research projects.
• Proven team management experience with 5-10 individual contributors.
• Strong background in AI security, privacy, and prompt injection research.
• English proficiency at least B2 level.

Nice to have

• Experience delivering research outputs into production or open source adoption.
• Research publications in ML security, privacy, safety, or alignment.
• Experience working on contextual security or prompt injection.

Culture & Benefits

• Competitive salary with bonus, equity, and benefits.
• Commitment to diversity, equity, and inclusion.
• Focus on ethical AI and public benefit.