Key Skills

Software

Labelbox

LightTag

OneForma

Redbrick AI

Sloth

SuperAnnotate

Top Subject Matter

No subject matter listed

Top Data Types

Audio

Document

Image

Video

Top Task Types

Audio Recording

Data Collection

Diagnosis

Text Generation

Freelancer Overview

AI Training Specialist focused on optimizing Large Language Models (LLMs) through rigorous Reinforcement Learning from Human Feedback (RLHF). I excel at evaluating model responses for factuality, safety, and tone, as well as drafting high-quality 'Golden Sets' for supervised fine-tuning. By combining linguistic nuance with a deep understanding of edge cases, I help bridge the gap between raw data and aligned AI behavior, ensuring models are both helpful and harmless for end-users

Labeling Experience

Education

Work History