Trust and Safety Intel Analyst, Model Behavior and Alignment

Google•Washington, DC

3h•$141,000 - $205,000

About The Position

As part of Google’s Intel Analysis team and Trust and Safety operations, policy, and enforcement, the analyst identifies, analyzes, and prioritizes threats across areas including deceptive behavior, emerging model capabilities, fraud, global events, violent extremism, and system vulnerabilities. Analysts combine research, internal signals, and cross-functional expertise to identify trends, forecast risks, and convert findings into machine-readable data for real-time intelligence integrations. This role focuses on model behavior risks: evaluating how AI systems behave in unexpected or misaligned ways, distinct from intentional misuse by bad actors. The analyst owns the model behavior risk portfolio across chatbots, multimodal assistants, agents, and robotics; defines collection requirements; synthesizes incidents and evaluation results into risk assessments; and distinguishes genuine misalignment from misattributed failures or hype. The work informs launch readiness, safety cases, and executive decisions, in partnership with safety researchers and policy teams to implement mitigations. The role sits at the intersection of AI safety and threat intelligence and welcomes candidates from AI safety, policy, intelligence, or Trust and Safety backgrounds.

Requirements

Bachelor's degree or equivalent practical experience.
Seven years of experience in one or more of the following: AI safety or alignment research, AI policy or governance, model evaluations or red teaming, trust and safety, intelligence or threat analysis, or risk analysis.
Experience reading and critically assessing technical AI research or evaluation results and communicating findings to non-specialist audiences.

Nice To Haves

Experience in AI safety, alignment, model evaluations, and AI governance, including familiarity with key labs and evaluators.
Experience in AI evaluation across modalities, technical fluency to assess risks, and scripting skills in Python or SQL for analysis.
Experience in threat modeling and intelligence generation under uncertainty, including AI-specific adversarial risks such as sandbagging.
Understanding of AI safety policy, regulatory landscapes, and frontier safety frameworks.
Knowledge of misalignment research, such as deception, evaluation awareness, and reward hacking, with the ability to evaluate evidence.
Ability to lead complex, multi-quarter projects and influence stakeholders without direct authority.

Responsibilities

Maintain a current, company-wide view of material risks across products and modalities, mapping risks to owners, mitigations, and remaining gaps.
Run regular cross-functional reviews of signals from investigations, evaluations, red teaming, user reports, external research, public incidents, and the policy landscape.
Connect incidents and weak signals to broader trends; distinguish genuine misalignment from misattributed failures and hype; and produce quick-turn and strategic assessments with confidence levels and recommendations for varied stakeholders.
Assess how new capabilities and deployment surfaces affect risk, contribute real-world evidence to safety cases, escalate unowned or under-mitigated risks, and track residual risk after launch.
Bring real-world signals into priorities and turn findings into taxonomies, threat models, and mitigations with clear owners.
Build AI-assisted workflows to automate research monitoring and signal triage, enabling analysts to focus on judgment-heavy work.
Own the model behavior risk portfolio across chatbots, multimodal assistants, agents, and robotics.
Drive collection requirements and synthesize incidents and evaluation results into clear risk assessments.