MSI TalentHub
← All open positions

Open position

Finance & Accounting Expert

Micro1

Remote · Remote, global, remoto5+ yearsUp to $90/hour equivalent

Finance & Accounting Expert (AI Benchmarking & Task Design)

Professional Summary

We are seeking experienced Finance & Accounting practitioners to design realistic, multi-step benchmark tasks that evaluate and measure the performance of AI systems. In this contractor role, you will translate real-world financial workflows—such as FP&A analysis, financial reporting, audit procedures, and reconciliations—into difficult, objective benchmark tasks and grading rubrics. No prior AI experience is required; your domain expertise and analytical rigor are key.

Key Responsibilities

  • Design multi-step, realistic tasks drawn from real finance and accounting work (FP&A, financial reporting, audit procedures, reconciliations) with reference files and clear instructions.
  • Define objective grading criteria and rubrics so multiple qualified reviewers achieve identical evaluation verdicts.
  • Build tasks that test high-level professional judgment and multi-document reasoning rather than simple information lookups.
  • Create or source authentic supporting materials, including financial statements, GL extracts, spreadsheets, and policy documents.
  • Identify and refine ambiguous or ungradable tasks to maintain top benchmark quality.
  • Consistently deliver approved tasks on schedule.

Technical Requirements (Must-Have)

  • Experience: 5+ years of direct, hands-on ownership in FP&A, financial reporting, audit, reconciliations, or accounting.
  • Review Standards: Proven experience creating or using structured review standards (audit programs, close checklists, review rubrics, or training assessments).
  • Tooling: Advanced Excel proficiency and comfort reasoning across multiple documents simultaneously.
  • Language: Strong written English proficiency (B2/C1 minimum).

Desired Skills (Nice-to-Have)

  • Professional certifications: CPA, CA, ACCA, CMA, or equivalent.
  • Prior experience with AI or LLM evaluation/benchmarking.

Opportunity Snapshot

  • Role Type: Contractor / Project-based (paid per approved task, ~10 hours per task)
  • Compensation: Up to $90/hour equivalent
  • Work Mode: Fully Remote (Global / No geographic restrictions)