Model Frontier Risk Analyst
Core
Analyze emerging AI safety risks, define risk mechanisms and failure modes, and translate findings into evaluation cases, benchmarks, and metrics for Seed foundational models.
Role type
Senior IC AI safety risk analyst
Builds
Evaluation frameworks, benchmarks, and metrics for AI model safety
Domain
Generative AI safety and risk management
Deliverable
production ML models
Required skills
Risk analysis, construct definition, experimental design, failure pattern identification, data analysis, written reasoning, verbal reasoning, problem-solving, end-to-end ownership, ambiguity resolution
Preferred skills
Behavioral science, HCI, UX research, fraud/risk strategy, model evaluation, SQL, Python, GenAI familiarity, cross-domain learning
Technologies
SQL, Python, Agents
Responsibilities
Research emerging AI safety risks using industry research, academic work, and expert input; Define risk mechanisms, scope, boundaries, and representative failure modes; Translate risk definitions into evaluation cases, benchmarks, metrics, and thresholds; Run exploratory analyses, pilots, and lightweight experiments; Review raw cases and evaluation results to identify failure patterns and iterate methodology