Key Skills

Freelancer Overview

I am a Senior AI Technical Trainer and Engineer with over 7 years of experience specializing in data annotation, AI training data, and large language model optimization. My background includes leading RLHF (Reinforcement Learning from Human Feedback) and SFT (Supervised Fine-Tuning) workflows for code-generation and software engineering models at top AI platforms like Outlier and Alignerr. I have authored thousands of high-quality training examples and 'Golden Responses' to serve as ground-truth data for fine-tuning models in domains such as backend development, blockchain, and secure API logic. My expertise spans prompt engineering, adversarial data auditing, and the use of advanced tools like LangChain, Pinecone, and Milvus. I am passionate about improving model accuracy and security through meticulous data labeling, annotation, and red-team assessments to reduce hallucinations and vulnerabilities in critical applications.

Labeling Experience

Education

Work History