Widade Harchan

Key Skills

Software

Mercor

Top Subject Matter

Large Language Models

AI Response Evaluation

Project Management/ Operations

Top Data Types

Text

Video

Document

Top Task Types

Bounding Box

Segmentation

Classification

Text Generation

Question Answering

Evaluation Rating

Object Detection

Freelancer Overview

AI Trainer / LLM Evaluation (Contract, Mercor Intelligence). Brings 12+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Mercor. Education includes Bachelor of Technology, New York City College of Technology and Associate of Applied Science, New York City College of Technology. AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

AI Trainer / LLM Evaluation (Contract)/Handshake AI

TextEvaluation Rating

Review and analyze model-generated responses across multiple quality dimensions, including clarity, accuracy, and alignment with the prompt. Apply structured evaluation methods to compare outputs and assign preference rankings based on overall effectiveness and reasoning.

Review and analyze model-generated responses across multiple quality dimensions, including clarity, accuracy, and alignment with the prompt. Apply structured evaluation methods to compare outputs and assign preference rankings based on overall effectiveness and reasoning.

2026 - Present

AI Trainer / LLM Evaluation (Contract, Mercor Intelligence)

MercorText

Evaluated AI-generated outputs using structured criteria and rubrics to identify errors and improve model performance. Provided objective feedback and rubric-based scoring to support AI model quality assurance. Performed ranking and comparison tasks to assess AI response relevance and accuracy. • Ensured responses aligned with guideline compliance and structured evaluation protocols. • Consistently applied quality assessment standards across multiple outputs. • Delivered detailed feedback on output performance and errors. • Supported model improvements by surfacing quality trends and deviations.

Evaluated AI-generated outputs using structured criteria and rubrics to identify errors and improve model performance. Provided objective feedback and rubric-based scoring to support AI model quality assurance. Performed ranking and comparison tasks to assess AI response relevance and accuracy. • Ensured responses aligned with guideline compliance and structured evaluation protocols. • Consistently applied quality assessment standards across multiple outputs. • Delivered detailed feedback on output performance and errors. • Supported model improvements by surfacing quality trends and deviations.

2025 - Present

Education

Work History