Jing Yu Lim

Key Skills

Software

Labelbox

Label Studio

Scale AI

Top Subject Matter

No subject matter listed

Top Data Types

Audio

Text

Top Label Types

Classification

Prompt Response Writing SFT

RLHF

Text Summarization

Translation Localization

Freelancer Overview

As a freelance AI Trainer, I experienced in leveraging Reinforcement Learning from Human Feedback (RLHF) to enhance the performance of large language models (LLMs). My role involves designing and crafting high-quality prompts and responses, which are crucial for training and refining LLMs to achieve improved accuracy and coherence. This work requires a deep understanding of AI training methodologies and the ability to create effective training data that aligns with the desired outcomes for language models.

Labeling Experience

AI Audio Trainer

LabelboxAudioEvaluation RatingAudio Recording

My experience ensures the delivery of clean, consistent, and culturally/linguistically sensitive data required for enhancing the robustness and accuracy of next-generation multilingual AI models. I bridge the gap between complex human language and machine learning requirements, directly contributing to improvements in Word Error Rate (WER) and overall model fluency.

My experience ensures the delivery of clean, consistent, and culturally/linguistically sensitive data required for enhancing the robustness and accuracy of next-generation multilingual AI models. I bridge the gap between complex human language and machine learning requirements, directly contributing to improvements in Word Error Rate (WER) and overall model fluency.

2025

AI Trainer

Scale AITextRLHFFine Tuning

I specialize in leveraging Reinforcement Learning from Human Feedback (RLHF) to enhance the performance of large language models (LLMs). My role involves designing and crafting high-quality prompts and responses, which are crucial for training and refining LLMs to achieve improved accuracy and coherence. This work requires a deep understanding of AI training methodologies and the ability to create effective training data that aligns with the desired outcomes for language models.

I specialize in leveraging Reinforcement Learning from Human Feedback (RLHF) to enhance the performance of large language models (LLMs). My role involves designing and crafting high-quality prompts and responses, which are crucial for training and refining LLMs to achieve improved accuracy and coherence. This work requires a deep understanding of AI training methodologies and the ability to create effective training data that aligns with the desired outcomes for language models.

2024

Education

Work History