QA Reviewer & Project Coordinator (On-Site - Seattle or Boston)

Location: On-site at a designated office in Seattle or Boston, United States

Company

hirify.global develops AI safety and healthcare research programs focused on evaluating and improving the behavior of AI systems.

What you will do

• Review AI content and expert evaluations for accuracy, safety, empathy, and policy compliance.
• Role-play realistic clinical scenarios, test AI models, and conduct red-teaming to identify failure modes and behavioral edge cases.
• Develop and refine evaluation rubrics, behavioral taxonomies, personas, scoring guidelines, and reviewer documentation.
• Document model inconsistencies and safety concerns, and provide structured clinical feedback to researchers and engineers.
• Track project timelines, deliverables, review queues, reviewer assignments, dashboards, and operational risks.
• Support staffing coordination, project meetings, action-item tracking, and follow-up across active programs.

Requirements

• Familiarity with ChatGPT, Claude, Gemini, or other large language models.
• Excellent written communication, documentation, organizational skills, and attention to detail.
• Ability to manage multiple priorities independently and collaborate effectively across teams.
• Comfort working in a fast-paced startup environment with evolving priorities.
• Ability to work on-site in Seattle or Boston.
• Willingness to sign comprehensive confidentiality and NDA agreements and work with sensitive mental health and AI safety content.

Nice to have

• Experience reviewing or auditing clinical work, especially involving serious mental illness, crisis intervention, or complex behavioral health populations.
• Experience with AI safety, LLM evaluation, prompt engineering, red teaming, trust and safety, or content moderation.
• Experience developing evaluation rubrics, taxonomies, annotation guidelines, or human-in-the-loop evaluation workflows.
• Project coordination, project management, reviewer training, or calibration session leadership experience.
• Familiarity with Google Workspace, Slack, spreadsheets, and project management tools.

Culture & Benefits

• Fast-moving startup environment with evolving priorities and ambiguous problems.
• Work focused on building safe, trustworthy, and clinically responsible AI systems.
• Regular project meetings, calibration sessions, and operational planning.
• Availability may be needed for occasional high-priority deadlines, including potential evening and weekend work.
• Strict confidentiality is required when handling sensitive clinical content.