Senior Finance Benchmark Designer for LLM Eval (Remote)

IXO Inc.; Northern (KY); Hybrid; USD 119,000 - 170,000; Full time

Benefits offered by this job

Remote work

105 USD/hr pay

Refer & Earn: $300 referral award

Job summary

IXO Inc. seeks senior finance practitioners to identify where AI analyses fail professional review and to define the behaviors a finance model must demonstrate. Work includes designing benchmarks, scoring criteria and evidence-based evaluations across corporate finance, asset management, private equity and more.

You will produce problems and reference solutions, calibrate judgments with researchers, and create repeatable evaluation processes for robust AI finance reasoning.

Qualifications

• At least five years of substantive finance work at a major bank, asset manager, private equity or credit fund.
• Senior decision responsibility at VP/Director/MD level; ownership of decisions and work products.
• MBA/MS/PhD or CFA/CPA/FRM credentials preferred but not a replacement for direct finance responsibility.

Responsibilities

• Design, review and calibrate benchmark evaluations for AI financial analyses.
• Develop realistic problems, benchmark datasets and domain tools to expose weaknesses.
• Produce instruction specifications and reference solutions with clear reasoning.
• Establish scoring criteria and calibrate judgments with researchers.

Skills

Senior Finance Benchmark Design

LLM Evaluation

Professional Judgment

Research Calibration

Benchmark Design

Education

MBA/MS/PhD in finance, economics, accounting or quantitative field

CFA/CPA/FRM or actuarial credentials preferred

Job description

IXO Inc. seeks senior finance practitioners to identify where AI analyses fail professional review and to define the behaviors a finance model must demonstrate. Work includes designing benchmarks, scoring criteria and evidence-based evaluations across corporate finance, asset management, private equity and more.

You will produce problems and reference solutions, calibrate judgments with researchers, and create repeatable evaluation processes for robust AI finance reasoning.