Senior Accounting & Audit AI Benchmark Specialist

Obsidian; San Francisco (CA); Hybrid; USD 120,000 - 180,000; Full time

Job summary

Cincinnatus LLC is hiring a senior accounting and audit domain expert to work with a leading AI lab's research and program management teams, improving how frontier AI models reason about real accounting and audit work. This is a full-time W-2 employment position with Cincinnatus LLC, with the opportunity to be placed at a leading AI lab as part of their extended workforce.

You will be provisioned with client-issued accounts and equipment, and will work inside the client's own tools alongside

Qualifications

• Active professional credential (CPA/CA/CIA/CFE/CMA) and degree in accounting or related field.
• At least 4 years of substantive accounting or audit experience at a recognized institution.
• Genuine specialization in at least one area (e.g., US GAAP/IFRS, SOX, tax, fraud examination).
• Senior-level progression with ownership of engagements or reporting cycles.
• Ability to work 40 hours per week for an initial 6-month engagement.

Responsibilities

• Data QA and reviews: Vet the quality of accounting and audit knowledge work tasks and model outputs.
• Write instruction specs and golden datasets for accounting and audit problems.
• Design benchmarks and domain depth with the research team.
• Calibration: maintain standards across client researchers and specialists.

Skills

AI fluency

Written communication

On-site collaboration

Education

Professional credential (CPA/CA/CIA/CFE/CMA)

Bachelor's/Master's in accounting

Job description

Cincinnatus LLC is hiring a senior accounting and audit domain expert to work with a leading AI lab's research and program management teams, improving how frontier AI models reason about real accounting and audit work. This is a full-time W-2 employment position with Cincinnatus LLC, with the opportunity to be placed at a leading AI lab as part of their extended workforce.

You will be provisioned with client-issued accounts and equipment, and will work inside the client's own tools alongside