Insurance Expert for AI Model Evaluation

Bring real-world underwriting, claims, and risk assessment expertise into GenAI model development by designing insurance-specific tasks, producing practiced solutions, and rigorously evaluating large language model outputs against structured rubrics. This role combines deep domain judgment with hands-on model evaluation to improve the correctness and reasoning quality of training data. The position is W-2 employment through Cincinnatus LLC, with placement on a leading AI lab team.

• Work with research and engineering teams to close knowledge gaps in underwriting, claims, and risk-assessment reasoning.
• Design challenging, domain-relevant insurance tasks that reflect real underwriting and claims practice.
• Write accurate, well-reasoned solutions for those tasks grounded in real-world practice.
• Evaluate AI model outputs against structured rubrics, providing clear written feedback on correctness, judgment, and reasoning quality.
• Develop and refine evaluation guidelines and scoring rubrics specific to insurance tasks.
• Collaborate with other subject matter experts to ensure consistency and accuracy in training data.

• At least 8 years of professional experience in insurance, such as underwriting, claims, actuarial work, or risk management, at a recognized organization (examples include AIG, Chubb, Allstate, Progressive, MetLife, Marsh McLennan, or equivalent).
• Prior hands-on experience evaluating LLM or AI model outputs against rubrics or structured scoring criteria, this is mandatory, please describe this experience in your application.
• Demonstrable career progression, for example moving from Underwriter to Senior Underwriter to VP of Underwriting or similar trajectory.
• Strong verbal and written communication skills, problem-solving ability, and interpersonal skills for cross-functional collaboration.
• Ability to engage reliably for at least 35 hours per week during weekdays.

• Employment type, W-2 employee of Cincinnatus LLC, placed as part of an extended workforce at a leading AI lab.
• Location, United States.
• Schedule, minimum commitment of 35 hours per week, weekdays required.
• This is an hourly role, employment relationship and workplace administration managed by Cincinnatus LLC, including payroll and benefits administration.

• Pay range, 60 to 80 hourly.

• Candidates must be able to work in the United States under W-2 employment with Cincinnatus LLC.
• Cincinnatus LLC is an equal employment opportunity employer, and does not discriminate based on legally protected characteristics.

When you apply, include your resume and a written description of your prior experience evaluating LLM or AI model outputs against rubrics or structured scoring criteria. Be prepared to confirm your weekday availability for at least 35 hours per week. Applications that explicitly describe the required LLM evaluation experience will be prioritized.