李伟

Key Skills

Software

No software listed

Top Subject Matter

Large Language Models

AI Agents

Quantitative Trading

Top Data Types

Text

Top Task Types

RLHF

Freelancer Overview

Model Fine-Tuning & RLHF Contributor. Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Internal and Proprietary Tooling. Education includes Bachelor of Science, 中山大学 (2016). AI-training focus includes data types such as Text and labeling workflows including RLHF.

Labeling Experience

Model Fine-Tuning & RLHF Contributor

TextRLHF

Participated in model fine-tuning and reinforcement learning from human feedback (RLHF) processes for large language model training. Collaborated in the evaluation, rating, and optimization of model outputs to improve language generation quality. Contributed to iterative model improvement cycles focusing on AI agent systems and quant trading modules. • Directly involved in RLHF as part of end-to-end model training. • Improved output quality through systematic annotation and human feedback. • Used internal/proprietary tools alongside PyTorch and TensorFlow. • Targeted applications include AI agents and quantitative trading AI solutions.

2023 - Present

Education

Work History