Remote Telecom AI Evaluation Specialist

mercor; San Francisco (CA); Hybrid; CAD 82,000 - 114,000; Full time

Job summary

Mercor is seeking a remote contractor to evaluate AI models for visual document understanding in the Telecom/Network domain. You will design and apply detailed ground-truth outputs and objective rubrics to measure model performance.

You will work asynchronously 15–20 hours per week, reviewing outputs and collaborating with SMEs to enhance data quality and model alignment with Telecom principles.

Qualifications

• Expertise in Telecom/Network domain.
• Strong understanding of visual document processing.
• Ability to create objective evaluation rubrics.

Responsibilities

• Evaluate the accuracy and depth of AI models on visual document understanding in the Telecom/Network domain.
• Author complex, grounded tasks with clear ground-truth outputs and objective rubrics.
• Review and improve AI model outputs to ensure alignment with domain principles.
• Collaborate with subject matter experts to enhance dataset consistency and relevance.
• Work independently and asynchronously to meet deadlines and improve AI model performance.

Skills

Telecom/Network domain

Visual document processing

Evaluation rubrics

Job description

Mercor is seeking a remote contractor to evaluate AI models for visual document understanding in the Telecom/Network domain. You will design and apply detailed ground-truth outputs and objective rubrics to measure model performance.

You will work asynchronously 15–20 hours per week, reviewing outputs and collaborating with SMEs to enhance data quality and model alignment with Telecom principles.