For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

Invite to Job
Junghee Han

Junghee Han

Biomedical Researcher & Interdisciplinary Analyst (Biochemistry & History Dual Major)

South Korea flagSeoul, South Korea
$30.00/hrEntry LevelMercorOneforma

Key Skills

Software

MercorMercor
OneFormaOneForma

Top Subject Matter

STEM & Biochemistry - High-Complexity Scientific Data Verification
Western Medieval History - Historiographical Reasoning & Logic Auditing
Creative Writing & Media - Narrative Optimization & Linguistic Tuning

Top Data Types

TextText
DocumentDocument
ImageImage

Top Task Types

RLHF
Evaluation Rating
Prompt Response Writing SFT
Question Answering
Text Summarization
Entity Ner Classification

Freelancer Overview

AI Data Evaluation and Verification (Academic Project). Brings 8+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include N and A. Education includes Bachelor of Arts, Yonsei University (2019) and Bachelor of Science, Yonsei University (2019). AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Entry LevelKoreanEnglishItalian

Labeling Experience

Development of Multi-Dimensional Evaluation Rubrics for Historiographical Reasoning & LLM Training

DocumentRLHF
Engineered a 4-stage, high-fidelity evaluation rubric to assess the ability of LLMs to synthesize complex historical narratives and socio-political theories (16th-century French Religious Wars and the formation of Modern Sovereignty). Designed 8+ rigorous criteria including "Textual Extraction," "Multi-Source Synthetic Reasoning," and "Cross-Verification" to eliminate AI hallucinations. Implemented a Dependency-based Logic System: Configured high-level analytical criteria (e.g., analyzing the 'Politique' ideology and 'Salic Law') as contingent upon the accuracy of primary source data extraction. Translated qualitative historiographical methodologies (Source Criticism) into a structured quantitative framework, establishing clear "Justification/Rationale" standards for each evaluation step.

Engineered a 4-stage, high-fidelity evaluation rubric to assess the ability of LLMs to synthesize complex historical narratives and socio-political theories (16th-century French Religious Wars and the formation of Modern Sovereignty). Designed 8+ rigorous criteria including "Textual Extraction," "Multi-Source Synthetic Reasoning," and "Cross-Verification" to eliminate AI hallucinations. Implemented a Dependency-based Logic System: Configured high-level analytical criteria (e.g., analyzing the 'Politique' ideology and 'Salic Law') as contingent upon the accuracy of primary source data extraction. Translated qualitative historiographical methodologies (Source Criticism) into a structured quantitative framework, establishing clear "Justification/Rationale" standards for each evaluation step.

2026 - Present

Education

Y

Yonsei University

Bachelor of Science, Biochemistry

Bachelor of Science
2023 - 2026
Y

Yonsei University

Bachelor of Arts, History

Bachelor of Arts
2023 - 2026

Work History

N

N/A

Business English Coach & Technical Translator

Seoul
2023 - Present
P

POSTYPE

Creative Writing Lead

Seoul
2019 - Present