Data Science Expert - Evaluation Specialist

Obsidian; New York (NY); On-site; USD 110,000 - 170,000; Full time

Job summary

Mercor partners with a leading AI research organization to engage experienced data scientists for a project focused on defining what excellent work looks like in real-world data science. You will design task-specific grading criteria and score work samples with rigorous written justifications.

Ideal candidates possess 5+ years in data science, deep fluency in experiment design, A/B testing, metric definition, and SQL/Python analysis, plus strong written communication for executive stakeholders.

Qualifications

• 5+ years of professional data science experience in industry.
• Background in business operations, product, or growth data science at top-tier technology companies.
• Deep fluency in experiment design and A/B testing, metric definition, SQL/Python analysis, and communicating findings to executive stakeholders.
• Exceptionally strong written communication.
• Detail-oriented, consistent, and comfortable having your judgment reviewed and calibrated against peers.
• Prior experience with AI training, evaluation, or human-data projects is a strong plus.

Responsibilities

• Design precise, task-specific grading criteria for real-world data science deliverables (analyses, models, dashboards, experiment readouts, and written recommendations)
• Score AI-generated and human work samples against those criteria, with detailed written justifications for every score
• Apply consistent, evidence-based judgment so that scores are reproducible and defensible
• Incorporate structured feedback from senior reviewers and iterate quickly on your work

Skills

5+ years data science experience

Experiment design

A/B testing

SQL

Python

Executive communication

Judgment calibration

Job description

1. Role Overview

Mercor is partnering with a leading AI research organization to engage experienced data scientists for a project focused on evaluating how well AI systems perform real-world data science work. Rather than producing deliverables yourself, you will define what excellent work looks like: designing task-specific grading criteria and scoring completed work samples with rigorous, well-reasoned written justifications.

2. Key Responsibilities

• Design precise, task-specific grading criteria for real-world data science deliverables (analyses, models, dashboards, experiment readouts, and written recommendations)
• Score AI-generated and human work samples against those criteria, with detailed written justifications for every score
• Apply consistent, evidence-based judgment so that scores are reproducible and defensible
• Incorporate structured feedback from senior reviewers and iterate quickly on your work

3. Ideal Qualifications

• 5+ years of professional data science experience in industry
• Background in business operations, product, or growth data science at top-tier technology companies
• Deep fluency in experiment design and A/B testing, metric definition, SQL/Python analysis, and communicating findings to executive stakeholders
• Exceptionally strong written communication
• Detail-oriented, consistent, and comfortable having your judgment reviewed and calibrated against peers
• Prior experience with AI training, evaluation, or human-data projects is a strong plus