AI Safety Expert (Seattle or Boston)

Location: On-site in Seattle or Boston, United States; ideally 20–40 hours per week.

Company

hirify.global develops automated tools and expert datasets rooted in psychology and powered by clinicians to improve safety in the AI era.

What you will do

• Evaluate AI-generated conversations, responses, and reasoning for quality, safety, and usefulness.
• Rate model outputs using structured evaluation rubrics and project guidelines.
• Annotate conversational data for AI training and benchmarking.
• Identify emerging risks, behavioral patterns, and model failure modes.
• Provide written feedback to researchers and engineers to improve model performance.
• Participate in calibration sessions and quality reviews while maintaining strict confidentiality.

Requirements

• Professional experience or subject matter expertise in psychology, behavioral science, social work, trust and safety, research, or a related field.
• Strong written communication skills and excellent attention to detail.
• Ability to learn and consistently apply structured evaluation frameworks.
• Strong critical-thinking and problem-solving skills.
• High ethical standards and sound judgment when working with sensitive or ambiguous content.
• Comfort using AI tools, Google Workspace, Slack, and web-based collaboration platforms; willingness to sign NDAs.

Culture & Benefits

• Temporary project supporting confidential AI safety and reliability initiatives.
• On-site collaboration in Seattle or Boston.
• Work with proprietary AI systems and sensitive content under strict confidentiality.