Bo S.

Key Skills

Software

Other

Don't disclose

Top Subject Matter

AI model training for Chinese language outputs and code evaluation

LLM output evaluation and code generation review

Chinese corpus training and localized LLM fine-tuning

Top Data Types

Text

Top Task Types

RLHF

Fine-tuning

Freelancer Overview

Self-directed AI training and RLHF capability (daily LLM assistant use; no formal job title provided). Core strengths include Other and Don't disclose. Education includes Bachelor of Science, National Chin-Yi University of Technology. AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including RLHF, Evaluation, and Rating.

Labeling Experience

Chinese corpus training and LLM fine-tuning capability (inferred from stated skills)

OtherTextFine-tuning

The candidate states they have a solid foundation for advanced AI model training tasks including Chinese corpus training and LLM-related optimization. This implies exposure to preparing or using Chinese text corpora and applying fine-tuning approaches to improve localized output quality. Their native Traditional Chinese proficiency supports culturally and semantically accurate training or refinement. • Capability in Chinese corpus training for LLMs • Participation in LLM optimization using daily AI assistant workflows • Localization-aware feedback for natural Traditional Chinese outputs • Emphasis on semantic detail and contextual subtleties for training outcomes

2025

LLM/code evaluation experience (prompt engineering and quality assessment; no formal job title provided)

Don't disclose

The candidate emphasizes evaluating AI-generated code quality across syntactic correctness, execution efficiency, bug risk, and reasoning consistency. Their training and practice include prompt engineering and assessing generation outputs for accuracy, relevance, safety, and logical consistency. This aligns with an evaluation/quality-rating workflow used in AI training pipelines. • Code evaluation of AI-generated outputs for correctness and efficiency • Bug and edge-case identification for generated code • Prompt engineering to elicit improved model behavior • Quality assessment across accuracy, relevance, safety, and logic

2025

Self-directed AI training and RLHF capability (daily LLM assistant use; no formal job title provided)

OtherTextRLHF

The candidate describes extensive daily hands-on experience with AI assistants for text analysis and code generation, indicating work aligned with AI training signal creation and iterative improvement. They also state they are capable of performing Reinforcement Learning from Human Feedback (RLHF) as part of AI model training tasks. This suggests familiarity with providing or shaping human feedback to guide model behavior. • Daily use of AI assistants for text analysis and code generation • Capability to perform RLHF training tasks • Evaluation mindset focused on accuracy, relevance, safety, and logical consistency • Likely involvement in human feedback loops for model refinement

2025

Education

Work History