Remote Visual Document AI Evaluator (Logistics)

mercor; San Francisco (CA); Hybrid; CAD 55,000 - 83,000; Part time

Job summary

Mercor seeks a Logistics & Supply Chain specialist to evaluate AI models for visual document understanding on a remote contract. The role requires 15–20 hours per week and focuses on assessing model accuracy with grounded tasks and clear rubrics.

You will collaborate asynchronously with AI research teams to enhance outputs and data quality, contributing to robust evaluation frameworks and benchmarks.

Qualifications

• What you must know about Logistics & Supply Chain in AI contexts.
• Strong skills in evaluating AI outputs and documenting ground-truth rubrics.
• Ability to work independently and coordinate remotely with teams.

Responsibilities

• Evaluate the accuracy and depth of AI models in visual document understanding within the Logistics & Supply Chain domain.
• Author complex, grounded tasks with clear ground-truth outputs and objective rubrics.
• Collaborate with AI research teams to improve model outputs and training data quality.
• Work independently and asynchronously to meet project deadlines while enhancing AI model performance.
• Develop evaluation rubrics and benchmarks for assessing AI-generated tasks and solutions.

Skills

Logistics domain

AI model evaluation

Visual document understanding

Independent work

Remote collaboration

Job description

Mercor seeks a Logistics & Supply Chain specialist to evaluate AI models for visual document understanding on a remote contract. The role requires 15–20 hours per week and focuses on assessing model accuracy with grounded tasks and clear rubrics.

You will collaborate asynchronously with AI research teams to enhance outputs and data quality, contributing to robust evaluation frameworks and benchmarks.