Key Skills

Software

Scale AI

Top Subject Matter

No subject matter listed

Top Data Types

Document

Text

Top Task Types

Classification

Computer Programming Coding

Evaluation Rating

RLHF

Freelancer Overview

Over the past 8 months, I have gained hands-on experience in AI training and evaluation through various projects at Outlier, all conducted entirely in French. I began by working on a French evaluation project, assessing model outputs for accuracy, fluency, and adherence to instructions. This role allowed me to refine my linguistic expertise and attention to detail. I then transitioned to a math evaluation project, where I created specialized prompts and evaluated model-generated responses for correctness, clarity, and problem-solving accuracy. Most recently, I contributed to a coding evaluation project, reviewing and scoring model code for functionality, compliance with specifications, and best practices. These experiences have strengthened my skills in data labeling, prompt engineering, and AI model performance assessment.

Labeling Experience

Education

Work History