Insurance Expert for AI Model Evaluation

Become an integral part of a pioneering AI lab''s GenAI team, where your expertise in insurance will play a crucial role in developing advanced Large Language Models. This position offers a unique opportunity to leverage your deep domain knowledge and hands-on experience in evaluating AI model outputs, ensuring that our AI training data reflects real-world underwriting judgment. Key Responsibilities

• Guide research and engineering teams to address knowledge gaps in underwriting, claims, and risk-assessment reasoning.
• Design complex, domain-relevant insurance tasks and provide accurate, well-reasoned solutions based on real underwriting and claims practices.
• Evaluate AI model outputs using structured rubrics, offering clear, written feedback on correctness, judgment, and reasoning quality.
• Develop and refine evaluation guidelines and scoring rubrics tailored to insurance tasks.
• Collaborate with other subject matter experts to maintain consistency and accuracy in training data.

• 8+ years of professional experience in insurance (e.g., underwriting, claims, actuarial, risk management) with a recognized, top-tier organization (e.g., AIG, Chubb, Allstate, Progressive, MetLife, Marsh McLennan, or equivalent).
• Mandatory prior hands-on experience evaluating LLM/AI model outputs against rubrics or structured scoring criteria; please detail this experience in your application.
• Demonstrable career progression (e.g., Underwriter → Senior Underwriter → VP of Underwriting).
• Availability to engage for at least 35 hours per week during weekdays.
• Strong verbal and written communication skills, problem-solving abilities, and interpersonal skills.

This is a W-2 employment position with Cincinnatus LLC, with the opportunity to be placed at a leading AI Lab as part of their extended workforce.

Hourly compensation ranges from $60 to $80.

Cincinnatus LLC is an Equal Employment Opportunity employer, committed to diversity and inclusion in the workplace. We do not discriminate based on any legally protected characteristic.