AI Safety & Model-Behavior Intelligence Analyst

Google LLC; Washington (District of Columbia); On-site; USD 141,000 - 205,000; Full time

Benefits offered by this job

Equity

Bonus target

Job summary

Google LLC in Washington, DC seeks a Trust and Safety Intel Analyst specializing in Model Behavior and Alignment. You will identify threats across AI systems, evaluate model behavior, and surface risks for leadership and product teams.

With 7+ years in AI safety, policy, or risk analysis, you will drive cross-functional assessments, develop risk taxonomies, and contribute to safety cases and mitigations across chatbots, multimodal apps, and agents.

Qualifications

• Bachelor's degree or equivalent practical experience.
• 7 years of experience in AI safety, alignment research, policy or governance, or risk analysis.
• Experience reading and communicating AI research to non-specialists.

Responsibilities

• Maintain current, company-wide view of material risks across products and modalities with owners and mitigations.
• Connect incidents and weak signals to broader trends and produce assessments for stakeholders.
• Assess how new capabilities affect risk and track residual risk after launch.
• Turn findings into taxonomies, threat models, and mitigations with clear owners.
• Build AI-assisted workflows to automate research monitoring and signal triage.

Skills

AI safety

Threat analysis

Policy communication

Data analysis

Education

Bachelor's degree or equivalent

Tools

Python

SQL

Job description

Google LLC in Washington, DC seeks a Trust and Safety Intel Analyst specializing in Model Behavior and Alignment. You will identify threats across AI systems, evaluate model behavior, and surface risks for leadership and product teams.

With 7+ years in AI safety, policy, or risk analysis, you will drive cross-functional assessments, develop risk taxonomies, and contribute to safety cases and mitigations across chatbots, multimodal apps, and agents.