Soon W.

Key Skills

Software

Google Cloud Vertex AI

Other

Top Subject Matter

AI quality control

code review

multi-agent orchestration

Top Data Types

Text

Document

Top Task Types

RLHF

Fine-tuning

Freelancer Overview

Lead RLHF & Quality Control for Multi-Agent AI Systems. Brings 3+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Internal and Proprietary Tooling. Education includes Diploma in Management Studies, Singapore Institute of Management. AI-training focus includes data types such as Computer Code, Programming, and Text and labeling workflows including RLHF and Fine-tuning.

Labeling Experience

AI Model Fine-tuning & Supervision Lead

TextFine-tuning

Directed fine-tuning and data evaluation initiatives for a cross-platform AI workforce solution. Administered supervised fine-tuning (SFT) with prompt and response curation focused on technical documentation and advanced system logic. Integrated expert demonstration and evaluation cycles to optimize enterprise-grade text models. • Constructed prompt engineering and data curation workflows • Coordinated enterprise-scale model evaluation • Merged local and cloud-based annotation environments • Focused on B2B software and documentation domains

2025 - Present

Lead RLHF & Quality Control for Multi-Agent AI Systems

RLHF

Led reinforcement learning from human feedback (RLHF) data labeling operations for a multi-agent AI platform. Evaluated and rated specialized AI agents’ outputs, focusing on code review and logical issue detection. Engineered automated pipelines for quality scoring and expert-in-the-loop model tuning. • Designed and implemented custom scoring and review layers • Developed red-teaming and self-healing mechanisms for AI pipelines • Oversaw expert review cycles for model improvement • Targeted labeling on software engineering and technical problem domains

2024 - Present

Education

Work History