Lead Analyst, Frontier Safety
Washington D.C., DC, USA +2 · Full-time · Posted Oct 23, 2026
- Location
- Washington D.C., DC, USA
Austin, TX, USA
Seattle, WA, USA - Experience
- 10 years of experience in data analytics, trust and safety, policy, cybersecurity, business strategy, or related fields.
- Education
- Bachelor's degree or equivalent practical experience.
About the job
Leads frontier safety red-teaming of Google’s generative AI products to identify high-consequence CBRN and cyber risks and drive mitigations.
What you'll do
- Design and conduct red-team assessments of AI products for CBRN and cyber capability uplift risks.
- Partner with Engineering, Research, Policy, and sibling RAIT teams on mitigations, autoraters, attack trees, and agentic-simulator threat personas.
- Direct external testing resources and present findings, risk assessments, and evaluation frameworks to executives and external stakeholders.
What they ask for
- Bachelor's degree or equivalent practical experience.
- 10 years of experience in data analytics, trust and safety, policy, cybersecurity, business strategy, or related fields.
Nice to have
- Master's degree or PhD.
- Experience with SQL, dashboards, CBRN and Cyber threat risks in GenAI, scripting/programming (e.g., Python), machine learning, or safety-focused tools and automation.
Pay
USD 171000 - 247000 base salary
Tools
SQL, Python
AI focus
Adversarially tests generative AI models, product surfaces, and autonomous agents for vulnerabilities, jailbreaks, and emerging catastrophic risks; develops evaluation methods and product mitigations.
Model-written summary · the original posting is authoritative